Please create an account to participate in the Slashdot moderation system

 


Forgot your password?
Close
typodupeerror
×
Science

Neural Networks In The Home? 154

Posted by Cliff from the intelligent-home-management dept.
Hougaard asks: "I'm investigating the use of neural networks in homes for a architectual project. Do you have a neural network that controls the light or the temperature in your home? Do you want one? What other features would you like to have in a real intelligent home? How should you learn and train the network? A remote with a 'Good' and 'Bad' buttons or something completly different? The only real life example I have found is the use of neural networks in elevators to predict elevator traffic. Yes I know that Cisco and others have the 'Internet House' - but that is just a home with a network - not really a revolution - and not very intelligent."
This discussion has been archived. No new comments can be posted.

Neural Networks In The Home? More

Neural Networks In The Home?

Comments Filter:

  • I can see it now.. (Score:1)

    by Anonymous Coward
    I can just imagine it, the house is approaching 150f as your pounding the "BAD" button on the remote, yet the confused neural net takes that to mean it's too cold and up goes the temp another notch.. And all the police find is a pile of ashes after you've spontaneously combusted. Mmm, Darwin award material. :)

  • Re:Neural Networks can't learn. (Score:1)

    by Anonymous Coward
    Learning is defined simply as any system that can improve it's performance over time or with experience. Neural Networks have this property, thus they are capable of learning. The fact that there is a "teacher" that modifies connection weights has little to do with whether something can learn or not. How many times have you learned something by people pointing out to you how wrong your conclusion was? This is a common learning mode. There is quite nice biological evidence of synaptic efficiency being improved by Hebbian learning in the brain. Finally, there are quite a few neural network systems that use unsupervised learning invalidating your point. Learning something substantial about the hype before you dismiss it.

  • What about traffic lights? (Score:1)

    by Anonymous Coward
    I would like to see better movement of vehicles through busy sections of a city. Lights that sense and learn patterns would help I think
  • Looping constructs? Just one means of expression.

    Consider (to give a trivial example -- ignore for the moment that it only operates on integers)

    def f(n):
    c = 0;
    for a=1..n:
    c += n
    return c

    While this uses a looping construct, it certainly can be modeled by a neural network (or, for that matter, rewritten without the use of loops).
  • As a former HVAC installation mechanic, I'll toss in my $.02.


    Your thermostat's working just fine (unless it's not level or is calibrated incorrectly). The sensation of heat or cold you feel moving from room to room is your duct system either sized wrong or balanced wrong. In the event of hot water heating (baseboard or radiators), excessive heat is more often than not bad thermostat placement.



    In-floor heating (aka radiant heating) *feels* worlds better than forced air because the floor is the radiator. You're standing on the floor, right? The reason it's not in more widespread use is that retrofitting it to buildings constructed without it is very expensive and not likely to work well,especially with thicker wood floors. It is very popular, however, in new construction using tile or stone floors.



    As for your personal situation of roasting, while the thermostat has not reached its set temperature, look on your duct system for a damper (most likely outside the room you're in) and close it down some. The vent for your room is oversized. If you've got baseboard or radiators, call a plumber to reduce the amount in your room.


  • No joke. From what I've read up on neural networks, basically what the author is talking about something raftloads ahead of current neural net tech, at least what's publicly available.

    And from what I've read up on, neural nets in the electronic sense are usually either glorified analog computing circuits, or digital simulations of the same event. They're using analog neural nets at MIT to keep costs down on robots, IIRC, but they really wouldn't do anything that current systems couldn't do for you.

    Perhaps a compromise between traditional control systems, neural nets, and traditional digital computing devices/software?
  • >How can you protect your home from ... Power
    >outages? Sure you can UPS the central unit, but
    >what about the lowly light switch on the wall?

    If the power is out, I don't think it'd matter if the light switch has a UPS, unless the light has one too.
  • the current setup of timers and pads that detect cars waiting for the lights are better. Neural Nets would most likely not take into account holidays and other problems.
  • What is the goal? If you want the lights to come on automatically, there is no need to worry about neural networks.

    If you want the dishes to wash them selves, I don't thine a neural network is going to get you anywhere by itself.

    So, I ask again, what is the goal?

    -j

  • I mean, its more like binary logic to me. Im about to move into a duplex with a friend that lives on the other side. We want a geek house. One of the things I really want is music on demand.

    Im going to take this music player im writing (only mp3's right now) and add a deamon mode. Right now it supports users rateing their music so they listen to what they want. Though I have been having a problem with my friends not likeing some of my music.

    What I want is for me and my friends that are over a lot to have a small key chain radio ID tag. So when your in a room it plays the music you want to hear, but when some one else enters the room, it takes what you both like and plays what is aggreed on. I dont think I need a nutral net for that. Unless I wanted something to learn on which songs you dont listen to as much (like you forward past it) and ones you search for. Then rate them up or down approately.

  • Well I have it set so you can add music at a desiered rateing. I was going to take an average of how much time you spend listening to songs, and if you keep skipping past it then it will get rated down. The oppisit will be true as well, if you seek out certin songs then they will get rated up.

    Right now the program doesnt learn, you just have to rate the music while its playing. I gave it a /. type rateing -1 to 5 system. Though I dont have a way to make it play anything other than the rateings you want to hear at the time (mainly 4-5 for me). Just while its playing you can rate that song down or up, and if it gets a rateing lower than what your listening to (4-5, and song gets rated to a 3) it bumps it out of the current playlist.

  • Dude, that's sick.
  • Day 0: Start boiler at set time, note time to get to temperature (x mins)

    Day 1: Start boiler x mins before set time !!

    Actually its probably more sophisticated than that in the sense the system may start heating the room depending on how cold it is (i.e the difference between the required and current temperature). Doesn't really require a neural net, just some means of averaging how long the system takes to effect a change in temperature when the system is calling for heat.
  • The only real life example I have found is the use of neural networks in elevators to predict elevator traffic.

    They tried it before at The Guides headquarters. They gave them a limited abiblity to see into the future, so they could be there ready to pick you up before you pushed the button. All that resulted was depressed elevators that wanted to stay at the bottom of the shaft.

    You'd think that they saw Frogstar Fighters in their future or something.

    --
  • In this scenario, Artificial Neural Networks are a tool. The question you should be asking is if they are the right(tm) tool.

    The original post does not give any specifics as to where or how you plan on using the Neural Networks. Whether or not a tool is correct depends on the kind of job/goal you want to accomplish and how efficiently it helps you in completing it.

    You should think carefully when you ask if a person would want to use a Neural Network in their home. It's a bit like asking a client "Would you want a Hydraulic Mounted, Photo-Diode based Solar Seeking Parabolic Reflector with your skylight?" -It's a lot of fancy words but not much information.

    ---

    Ok now would I want a Neural Network in my home? In actuality I have an X-10 enabled apartment hooked up to my PC upon which I have a Neural Network based speech recognition interface (BP + K-SON). This is a project I did for fun. If this were a product, I'd be using another tool. Maybe IBM's ViaVoice.

    Can I see a real use for neural networks in the house? Absolutely. One day I want an agent that takes into account many context variables:-

    1) who is in the house
    2) where they are in the house
    3) what they are doing in the house
    4) what mood they are in

    These types of questions are suited to Connectionist type systems. An agent like this would know that I am in the bedroom programming so I normally want the lights dimmed in the bedroom and off everywhere else. On the other hand it would know when I am upset and would not deign to make decisions for me based on the fact that I might get upset at it.

    An agent like this would also be written using a variety of "intelligent" programming techniques, possibly using Production Systems, Fuzzy Logic, Neural Networks, Genetic Algorithms, etc.

    ---

    If you are interested in a basic introductory text, you might check out Stan Franklin's "Artificial Minds".

    A good text (the only one I know of too) on emotion recognition is Rosalind Picard's "Affective Computing".

    If you want an quick intro to context based programming, check out the latest IBM Systems Journal featuring MIT Media Lab's current research projects. Actually, there are several papers here that might interest you:

    P.530 Out of Context: Computer systems that adapt to, and learn from context. - H. Liebermann, T. Selker
    P.705 Toward computers that recognize and respond to user emotion. - R. W. Picard
    P.861 An installation of interactive furniture. - O. Omojola, et al.
    P.880 Context-aware design and interaction in computer systems. - T. Selker, W. Burleson
    P.892 Sensor Systems for interactive surfaces. - J. A. Paradiso, et al.
    ---

    I hope this has been helpful,

    Frank Fletcher (Ailima)

  • Yes, a neural network controls my home. It's this nifty thing called "brain" that I make sure to carry with me everywhere I go. But I suppose an artificial neural network capable of doing stuff for me when I was away would be pretty cool.

  • a house that costs this amount of money would have a dishwasher that didn't run while I was in
    the shower.....and be quiet enough to run in the middile of the night.
  • See this [colorado.edu] web page to read about Mike Mozer's adaptive house. He actually lives in it, and large subsystems in the house are under neural network control.
  • I just this experiment on TV awhile back. They were trying to make the house learn how you liked things. That way if you walked into a room it would set the lighting and temperature to what you liked. If you fell asleep on the couch it would change the music, the volume of the music, and the temperature, even turn off the tv for you. Neat stuff.
  • See
    http://www.cs.colorado.edu/~mozer/house/
    for the details.

    World class application of machine learning.

    -- Malcolm
  • I've often considered turning my thermistat into a "smart thermistat"

    To do this, I would modify each vent in my house to use a motor to turn a screw that would open and close the vent. I would also attach a thermistor to measure the temperature coming out of the vent. Finally, I would use some sort of wireless transmitter in combination with a thermistor to transmit the actual room temperatures back to the thermistat.

    I've often found that the biggest problem in most thermistat setups is that the thermistat sits somewhere it shouldn't such as near a vent or window. This fools it into thinking the temperature is either much cooler or warmer than it really is. By using a wireless transmitter, it would be easy to relocate based on window locations, vent locations and even furnature arangement.

    Josh
  • Not necessarily. The neural net would likely be programmed on a 7 day cycle, since with a full 365 day program, it would take too long to train up.
  • When I was working for a company doing commercial HVAC, we found that chills tended to be psychological. By putting a thermostat on the wall, but programming it to be inactive, we found that most people were then satisfied with the heating control. i.e., they thought they were controlling the temperature and were thus happy, though in reality they had no effect.
  • Yeah, I worked as a tech rep for an HVAC company, and a lot of people don't realize that at the stat the temp may be fine, but not all parts of the building are at that temp.
  • The TIVO attempts to find programs that you like and record them for you.

    It even records shows it "thinks" you might like and offers them to you. Has anyone who has used a tivo extensively found this to be any good?

    --buddy
  • They aren't even good for a HVAC use. The typical problem with the HVAC system is the feeling of chills. The thermostat will have things under control but some people just feel like the air is colder than it actualy is. It may be the result of the rapid cooling or the blower fan being on or the humitidy. A neural net could learn to avoid the chill factor if it had input for thouse other variable but so would a 4 bit cpu if given the right sensors.
  • I don't know where you get your shirts but if you wash the new ones with a slight amount of bleach (1 table spoon or so) you will quickly find out if its color is going to come out. If the shirt changes colors, take it back since its dyes are defective. Most mens stores (in the US) will take back shirts without question within a week with a reciept. So far I only find less than 1 in 10 peices of clothing have defect. If I'm asked for a reason for the return, I put down "unreasonable cleaning requirements". Chemist worked hard to make permanent press and non-fading colors. Why reward the cheap knockoffs?

    What I want is a dryer that won't let clothes wrinkle. I've almost got one now but the damn thing beeps every 3 minutes and gives up after 2 hours.

    Has anyone else noticed that laundy cleaning technology hasn't gone anywhere in the last 40 years? The current line of dryers work the same way as my mothers 30+ year old speed queen but the new models have more curves in their desing and don't looke like a big white box. Something that I've wondered about for quite a long time is can a dryer be made to use flash evaporation? Just have a strong box that will hold clothes and suck all the air out till it gets below the water vaporization pressure. It seems like today that might be cheaper than the current approach which is to riase the temperature and use lots of air.
  • I know lots of people who spend so much time in their Sports Utility Cars (SUC) that they can call them home.
  • Of course, what I really want is somethat that scans TV listings and tells me when something interesting is going to be on. Or something that records off the radio, but only archives music it thinks I'll like.
    Umm...you mean something like TiVo [tivo.com]? Over time, it figures out what kind of stuff you like and starts recording things it thinks you'll like.

    It only does TV, though...if it also did radio, that would be the sh*t. (The problem is that radio schedules often aren't published in the same manner as TV schedules. A radio station's website might have a listing of what it's playing (here's a local example [kxnt.com]), but I've never seen a schedule for all of the local radio stations, compiled in one publication, anywhere in the States. They probably figure that someone who listens mainly to stuff like Nine Inch Nails or Stone Temple Pilots doesn't give a rat's ass about what's playing on a station that plays the Backdoor^H^H^H^Hstreet Boys or Britney Spears, or something like that.)

  • Dear Sir, I read your little question here at ./ and I must wonder wether you actually know what a neural network is. For your elevator example I would suggest you use regular statistics which will give you an at least equally good result with less fuzz. In the meanwhile I suggest you do the following: (1) Go over the sum-function and (2) get a couple of regular paper boxes. Ask everyone taking an elevator near you to put a penny in the box that represents the time-group in which the person used the elevator. Put these boxes at all levels. This will make perfect sence to you when you have researched to find out exactly what a neural network is, give you data for your statistics on which your elevator will operate and perhaps even make you a buck.
  • Just throw a few motion sensors around so the "room" can know when someone enters. NNs don't store information in a retrievable form, so there aren't any privacy concerns.
    Cheers,

    Rick Kirkland
  • Flush the pod bay toilet, Hal.

    [silence]

    Please flush the pod bay toilet, Hal.

    [silence]

    Hal, PLEASE flush the pod bay toilet and start the dishwasher on rinse-and-hold cycle.

    I'm sorry Dave. I can't do that.

    k., who wants a Monolith that color-coordinates with the fridge and stove.


    --
    "In spite of everything, I still believe that people
    are really good at heart." - Anne Frank
  • Neural networks, like Slashdot first-post fanatics, are slow learners. I'd love a smart controller for my heater (regardless of the underlying implementation). But figuring that I'd press the bad/good button about 3 times a day, I'd probably be dead before it figured out my preferences.
  • I just bought an electronic thermostat for my house. It's the kind that you can program to set the temperature back at night and while you're away during the day to save energy.

    The interesting part is this: it has an optional feature where you can specify a time and temperature, and it will "learn" over the course of several days when to start the furnace so that the temperature is achieved at that time.

    Now, I have no idea how this feature is implemented, but it's a classic neural net sort of problem.

  • Actually as far as temperature, where I used to work they tried implementing a neural network to control the heating/cooling of the building. We were using neural networks in our product at the time, so it wasn't very difficult to stretch the program over a couple of different inputs.
    The idea behind it was that everyone would have different preferences as to the temperature of where they were, as well as different drafts etc. The building was split into something like 14 zones, which allowed different heating/cooling based on location. So another hope is that the person who sat on the northeast corner who was always cold could get a little extra heat from the nearby zone even though they were in the zone where everyone else was always warm.
    A neat idea, but in practise it didn't work so well. Basically everyone was given the option to say what temperature they would like it to be. And the system would try and make that happen. Because everyone has a different idea of temps some people thought it should be 68, while others thought 74. They ended up having the largest heating bill ever in 1 month and so management decided to cancel the test.
    My ex-boss had the idea that people should have instead voted for whether they were too cold/too warm rather than trying to set the temperature directly. Maybe it would have worked better.
    I also think the problem is the issue of learning time. Before a neural net figures out what's going on, you don't have a very nice system. The more complex the system (and therefore the greater the need for a neural net), the longer the learning time, and the greater amount of time before good returns can be seen. And especially in a system that you don't know whether or not it's going to turn out well (like the temp control), you may not be able to afford that learning curve.

    But an interesting idea nonetheless.
  • Neural nets in the home are already starting to appear - albit in a rudimentary form. Take Fuzzy Logic for example - many new theromostats and AC/Heaters can now run at variable speeds. No longer are things just On/Off, but can operate at a graduated power. Andother example are the simple motion lights - that turn on when they sense movement, and can automatically turn off during the day. The basic technology is already here.

    The next step is to start integrating all these disparate technologies into a centrally controlled unit. Look at the X10 (www.x10.com) They are making good attempts at automating existing home appliances with some sort of automated control.

    So, we have some rudimentay fuzzy logic, and some automation. Now, the next step is to combine the two into a "intelligent" central point. but is this really where we need to go? We will now have a single point of failure for all home functions. If you blow a chip, the house is out of order until the central unit gets fixed.

    Also, it takes another generation of devices. The neural devices will have to operate either automously, or together as a collective. Which is perfered? How can you protect your home from hacking? Power outages? Sure you can UPS the central unit, but what about the lowly light switch on the wall?

    We are headed that way, but there are a lot of little details to work out first.

    "Some days it ain't worth chewing through the leather straps"

    - Hondo

  • Strange... That picture looks amazingly like the drawings of Irish Catholics in the 19th Century, and Jews of the 20th Century.

    You should really take a look at your family history. At one point in history your family was subject to the same pathetic attempt to put a bigot boot to their head.

    The fact that you've posted anonymously only confirms my impression that you are afraid to confront your past. Its time for you to move beyond having to put down others to affirm your own existance. Be proud of something that isn't an artifact of your birth.

    Or can you look in the mirror and find anything other than your skin color to be proud of?

  • NN (Score:1)

    by abes ( 82351 )
    Neural networks by themselves do not automatically make something 'intelligent.' They are one tool available to someone trying to solve an AI-related problem. They will not automagically make your house superintelligent. There are also several classes of neural networks, such as feed-forward backprop (which is a commonly used class of NN, but also of a lower computational model than Turing Machines), and recurrent neural networks (which are of the same computational model of TM, but tend to be harder to train). Other AI methods that are non-NN include: fuzzy logic, minimax, alpha-beta, etc. (there are a lot more, but I'm feeling lazy). None of these methods are really better or worst than a NN, just different. Depending on your task their ability to search through a given problem-space may be better than other methods (theres a lot of experience/guess-work involved).

    Most likely places where you might want to employ any type of AI would be in situations where you needed certain types of adaptation. It is important to know what method you are employing is capable of beforehand, otherwise you will end up with a badly-behaving system. For example, if you took a perceptron (a single-layer feedforward NN) and tried to get it to classify an XOR problem (the classic breaking point of the perceptron), it would fail. But it can classify other types of problems great.

    There are a few classic applications of AI in the house, like temperature. Even this application is non-trivial due to fluctuations in temperature just across room. You will find most applications will have to take into account the world is a chaotic place (and system) [which is why an adaptable system is needed, but also makes is non-trivial].

  • As a starting point you might want to check out "House_n: The MIT Home of the Future" at http://architecture.mit.edu/house_n/

    Other useful links can also be found at http://home-automation.org/
  • If you haven't already, let me highly recommend reading the book The Age of Spiritual Machines by Ray Kurzweil. It's got some amazing insights about the next 100 years, as well as a fairly in-depth discussion of neural networks and algorithms for them. It also covers other methods for creating "intelligent" machines such as recursion (used in chess-playing).

    Here's the Web site for the book [penguinputnam.com], and also Ray Kurzweil's site [kurzweiltech.com].
  • Moderate this UP
  • I think that fuzzy logic is more appropriate for home automation projects like climate control.

  • There have been experiments with "learning" homes before, such as the "ACHE" project. Some papers on "applications of machine learning" by Michael Mozer (Colorado U) make for a very good read.

    Michael Mozer's Publications page [colorado.edu]

    The Neural Network House [colorado.edu]

    An Intelligent Environment Must be Adaptive [colorado.edu]

    There was one more reference (which I can't locate right now - sorry) which was an excellent set of web pages which described this project. I seem to recall that it even included Java applet simulations of the reactions of the house to occupancy and other stimulous.
  • I think the best use of the neural net would be for speach recognition. How much would you really want your "house" to "learn?" I have some lights on X-10 and they work quite nicely on a very specific set of rules. The porch should go on when it's dark. The living room should go on when it's dark and there are people in the room (or I specifically ask for it to be on). The fan is on when I want it on.

    What could a neural net do that you would want it to learn? If I want the lights on every time I go into a room, that's easy enough with the standard, binary logic. Do I want it to start thinking that I only want that when I'm not wearing a jacket?

    I suspect the the only thing that wouldn't be "definte" would be trying to determine what I said. Maybe I mumbled and traditional software would choke. Maybe I'm eating. Maybe I don't want it to respond to other people.

    Think about Star Trek: how does the computer know that when the crew member says "Computer" they're actually talking to the computer? Perhaps the neural net could detect the difference between the user talking to the system rather than about the system.

  • But fuzzy logic systems can are easier to set up if you know what you want them to do for at least some cases.
  • Divide and conquer is a tried and true approach. You probably don't want one single, large NN in this application. I'm thinking about one for temperature regulation, one for hot-water regulation, one for out-side lighting, one for in-door lighting and one for tracking human presence, etc.. Then you can build interdependencies and feedback cycles, feeding selectively - say - human presence tracking into the various applicable NNs. My gut feeling tells me this might work. Maybe. The very best thing, is to simulate and see what happens :)

  • You train your house, and everything seems to be going fine, then one day, you do something different, how does the house respond? When you finally get a date after years of solitude and bring her home, does the house start randomly turning lights on and off and scrambling eggs?

    Even disregarding the possible faults, what are the benefits? "Oooh, my smart house knows to turn off the lights and turn down the thermostat when I go to bed." How about an "I'm going to bed" switch? Same results, simpler design, more predictable and configurable.

  • It doesn't have to be visible, just on your person. At school here, we have ID cards that can open doors by merely being within a certain proximity of the reader. In the future, that proximity can probably be refined enough for this whole shindig, as well as making the cards small enough to be forgetable.
  • "Smart Homes" are cheap. $100 at www.smarthome.com [smarthome.com] will get you a good starter kit of lamp packs, serial interface, etc. So while the actual number of Slashdotters using X-10 may be slim, there's not a huge reason why it has to be.

    A system that learns from the occupant would be exactly the reason to use neural nets for X-10 macro programming. Why sit down and program the lights to come on "around the time I get home" or "about 20 minutes before sunset" when those times change, and that change can be learned?
    ------
    WWhhaatt ddooeess dduupplleexx mmeeaann??

  • Yes, next thing you know, they'll become frustrated with the mindless business of going up and down, up and down, and experiment briefly with the notion of going sideways, as a sort of existential protest, demand participation in the decision-making process and finally resort to squatting in basements, sulking. Maybe then I can get a job counseling nerotic elevators, as The Guide mentions.
  • ... the water coming on, scaulding hot... DOH! Freezing Cold... DOH! Slightly less hot... DOH! Slightly less cold... DOH! (and on and on for 5 minutes until it settles on a good temperature).

    This is the way your neural net does it, until it learns.

    In the same way a neural net in your shower would learn your user preferences without you having to explicitly set them, or even think about it.

    Of course you'd have the option to set them yourself if you liked...
  • > They don't learn like humans do, but a (three
    > layer) neural net can express *any* function.

    So can a lookup table.

    And just like a lookup table, an 'n'-layer neural network can't do itteration, counting or any other looping construct.

    Don't get me wrong, neural networks can do itteration brilliantly. But not when they are shoehorned into 'n'-layer configurations for the benefit of external training programs.
  • One fiction that you will hear over and over again is that neural networks learn. Sadly, they do no such thing.

    The "back propagation", "delta rule" or whatever else that is being used is an external program that edits the strengths of some of the connections in the net.

    Neural networks are merely an obfuscated programming language that is basic enough that it can be tweaked by a watchdog program that is keeping an eye on its results. Beware of getting caught up in the hype.

  • But not when they are shoehorned into 'n'-layer configurations for the benefit of external training programs.

    Have you heard about backpropagation learning for recurrent neural nets?

  • You are confused about the difference between the neural net as a mathematical model and its computer implementation.

    Mathematically speaking neural network is a function with certsain parameters. Learning is a way to adjust the parameters to fit the function to the actual data.

    Just as with people there is a difference between performing a certain task and learning to do it.

  • No, no, it's more like Douglas Adams; remember the clairyoiant elevators in Hitchiker's Guide to the Galaxy? (hmm, maybe it was book 2)

    Or, of course, the annoyingly cheerful ship computer Eddy, or the drink machine that would always produce a substance that was almost, but not entirely, quite unlike tea, or Marvin the paraniod android, or...

    I'd say that Adams predicted the de-evolution of technology pretty well.

  • Amen bro :).

    Yah, how about smart people for a change :).

    When you have machines being able to predict what humans want, it's probably because the humans have become stupider rather than the machines becoming smarter.

    Machines should do what we tell them. Not try to guess. Only in dangerous situations should there be prompts e.g. "Crash imminent! Pull up! Pull up!".

    I want machines which will quickly do what I want. Not try to second guess me. And allow me to specify _exactly_ what I want if necessary.

    Basically I've been thinking of a wearable device that will let me bookmark my favourite temperature settings, and let me use them wirelessly from room to room in a "smart home". Same with music and other stuff.

    If I don't turn on the lights when I walk into a room, that's because I want the lights off. Doh!

    If I really want something that can second guess me, I'll hire a good butler. Not everyone can be a decent butler, so I doubt a machine could do that.
  • I had one installed a little while ago. Actually it was so big it had to go underneath my house. It has been working well for a few years now - not too much to complain about, occasionally it does some crazy things, but I can't complain. I have to be careful not to turn it off or it will really throw the whole place into chaos.

    The salesman tried to sell me an older previous (used) model called 'Deep Thought', but I wanted something that was more scalable, now that 2.4 is out ...
  • If neural networks are involved, there's no need for a badge, just systems to gather input that would allow the house computer to recognize individuals by body/face/voice. I can't imagine being okay with wearing a badge around the house and making sure it's "visible at all times".
    ---

    Dr. Trevorkian
  • Well, *I* got it the first time. =^P
    ---

    Dr. Trevorkian

  • Do you have a neural network that controls the light or the temperature in your home?

    Yes, I do. I call it a "brain", and it works great. Some might fault its need for constant maintenance and periodic down time, but it genuinely does an unbeatable job of setting the light and temperature exactly as I want them. It's also nice and expandable, capable of taking on all manner of additional functions not in its original design. I've had my "brain" for a long time now, and although it may not be a speedy as some of the newer models, it's always worked like a champ. I guess you could say I'm kind of attached to it.

  • The thing about smart elevators kind of reminds me of the part in the HitchHiker's Guide, when Zaphod was at The Guide's headquarters, all the talk about Sirius Happy Verticle People Movers?

    ...

    Yeah, that was pretty funny.
    -------

  • While browsing through this discussion I noticed that there are a lot of misconceptions in relation to what a neural network is. A lot of confusion emerges from the fact that the term itself is ill-defined and often misused in semi-popular publications, but there are a few things that I would like to point out...

    First of all a lot of people seem to confuse the theoretical concept of neural nets with how they are implemented. These are two seperate issues! Someone wrote in a comment that back propagation networks can't learn because they use an algorithm to adjust their weights, but this is like saying that an object oriented design is bad because I implemented it without the use of classes (or structs if you like). In fact this person could (in his/her mind) have made an even stronger statement by saying that most neural nets are entirely implemented as c-code algorithmes, but this is obviously beside the point. The fact that this is the case is just because the computer as we know it is a great tool for exploring new theoretical frontiers because it's cheaper than building special purpose hardware, it's flexible and we humans like to use symbolic representations.

    Second, there are several classes of neural networks. Back propagation is just one of them, but there are many more (e.g. interactive activation and constraint satisfaction). The only thing they have in common is the concept of distributed processing and representation. Some models use clusters, others layers and some no hierarchy at all. Some models use feed-forward activation, some bilaterale activation, some local inhibition and others combine several strategies.

    Third, the potential of neural nets in general is often underestimated (at least I think so ;)). Many posts in this discussion are aimed at what neural nets can not (yet) do. It's like reading a m$cr$s$ck-newsgroup on linux! While the fact is that a neural net can (in theory) do what any other computational model can do and much more! A neural net can 'learn' to perform tasks that are impossible to model in a 'traditional' computational model because the problem space is too complex for us humans to model. (note: in some cases we can retrieve the distinguising parameterset through hierarchicle clustering which then allows to write a conventional algorithm... thank you neural nets!!).

    Finally, to address the question asked in the initial post, I think that using neural nets to regulate temperature and light in buildings is not a verry good idea. These are well defined problems which don't require extensive learning and are case based. They can be resolved (and are?) in a much easier and cheaper way..

    cheers,
    DaBs

  • -57 Celsius! (Score:2)

    by Anonymous Coward
    New record low temperatures in Siberia!

    -57 Celsius (-70.6 Fahrenheit)

  • I wouldn't suggest neural networks for controlling house lights, save for the possibility of heating/cooling systems.

    Neural networks are meant to try to 'black box' complex behavior into a nice package, with the ability to learn and adapt from past and present behavior. While the running of a household is certainly a complex pattern, it's TOO complex with too many variables to be effective. NNs can also over or under predict, and I'm sure there are things that you do not want to go on or off without your input.

    A NN *could* help with efficient heating and cooling of your house, of course; you'd need to have a large data set of times, indoor and outdoor temps along with windspeeds (or wind chill factors) for about a year to get an effective yearly cycle in place, then with the time and conditions, it should be easy to have the network control the temperature and minimize energy use while maintaining a comfortable room. This is because all those factors can be realized as a complex yet predictable pattern (as there is no human element involved), and thus a trained NN should be able to do the trick.

    What you'd probably want for the rest of the house is the use of a rules-based logic or fuzzy logic. This is more adaptable to individual users (specifying their own rules), and it is more than adequet for house control.

  • The basic utility of neural networks is basically the same as "genetic programming" .. they avoid the necessity of having to describe a solution to a complex (or merely subtle) problem.

    The trained network or the evolved program solves your problem, but it's basically "black box magic" -- you never really will understand completely how it works or how it was arrived at. Both can also exhibit unexpected properties.

    They're overkill for most problems where you CAN describe an adequate "deterministic" solution. Neural nets also require a fair amount of overhead, too.

  • Generally most folks don't consider X-10's to be "Smart Houses". An argument could well be made for them, particularly the more elaborate setups but in most cases what's referred to as a "Smart House" is more then the extended lightswitch-type devices X-10 modules usually are.

    Sensing, monitoring, complex-responses, etc. would be more in line with what is often meant. Your definition may of course vary widely.

    That said are you aware of anyone doing any adaptive/learning/non-declarative stuff with these rudimentary devices?

  • Michael Mozer [colorado.edu] of U. Colorado CS department wired his entire house with sensors and controls connected to neural networks and other machine learning systems. He did this at least five years ago, so the idea is hardly new. The house has a web page [colorado.edu] with an overview and another link that shows the status [colorado.edu] of the house.

    One great story about the house has it that Mozer's students would call his house whenever the toilet sensor showed that he was sitting on the can for more than a minute.

    I believe that particular sensor was later disabled.

    --GWF

  • This is the right idea, but it doesn't require a neural network to do it for you. It just requires a computer that can tell when you are awake or asleep!

    The thing about neural networks is that they are good for making fuzzy judgements about patterns based on trained input. But I KNOW the way I like my lights to be, what temperature I want and when, and there aren't too many possibilities! Once I program everything into the thermostat or X10, I'm likely to be fine -- I'm not sure what a neural network would DO in this case.

    For the media lab idea, you COULD use an NN whose inputs are things like the room you are in and some notion of the amount of movement you have made in the past few minutes, but you need to be careful here -- you don't want it turning the lights off when you are sitting on the couch quietly reading.
  • The basic utility of neural networks is basically the same as "genetic programming" .. they avoid the necessity of having to describe a solution to a complex (or merely subtle) problem.


    I know, but I believe the hassles one goes through in the learning process aren't worth the final result, specially in a very deterministic environment like a house. As another reader pointed out, you wouldn't like the net to deal with events like waking up at 4 am for some random reason, a fact that isn't likely to repeat itself.

    Flavio
  • Dont you think a realy intelligent house would be completely voice activated for those who could speak anyways. Id prefer to scream at my walls that they are stupid idiots for turning on the dishwasher in tthe middle of the night instead of having to fumble around for a remote control and figure if im telling it its good or bad. I guess having a battery powered system would be an important feature, put good use to an old 486 laptop that has no other use than to also control the houses security system. And Solar Power would be a good feature to build in as well.
  • I always thought that once computers have learnt to recognise when we appriciate their actions they will become hell of a lot more helpful to us.

  • There is a serious "engineering tradeoff" with neural networks: You are exchanging reliability and precision for creativity and flexibility. How much unreliability and imprecision are you willing to stand in your home automation?

    Imagine if your goldfish was running the lights in your family room ...


    *** Proven iconoclast, aspiring epicurean ***

  • The way the house knows it did something "Bad" could be when the user intervenes. For example, someone turns a light on at 5:30-ish pm for a few days it figures out "This person wants a light on this time of day."

    The only real problem with this is how do you collect information to base these conditionals on. The example above used only time. Time, time of day, seasons, etc are pretty easy but do you want cameras following you around the house or even pressure sensors? When someone walks into the room, light up except between the hours of 8am to 6pm (varying on time of year) when the giant window is collecting lots of light.

    Anyway, my point that got lost somewhere up there is the more information you have, the better (hopefully) the system can predict wants and needs. However how much information do we want these systems knowing?
  • The problem with carrying around a badge around at home is that I wouldn't do it. My patterns at home are vastly different than when I'm at work or school. When I'm at work it can be assumed that I'll be doing various things that make the carrying of tracking devices fairly unobtrusive, however most of the ways of tracking this assume that I am wearing pants. This is a very reasonable assumption at work when I am at work I do wear pants and the accompanying wallet, key ring, cell phone and PDA. However, this all changes when I get home. The wallet, key ring, cell phone and PDA get deposited on the coffee table and the pants with pockets get dropped in the hamper then I put on cutoff sweat pants (no pockets and eat dinner, watch TV, surf the net, talk on the phone or whatever I'm planning on doing that evening. How is the system going to effectively track what room I'm in without the items that I customarily carry? Is it going to be confused that my shoes (yeah, just like in Enemy of the State) are on the mat by the door, the wallet/cellphone/PDA pile is one the coffee table, the pants/belt is in the hamper, the watch is behind the kitchen sink (took it off to wash dishes)? Rest assured that I am not standing by the front door for hours, nor am I standing on the coffee table or hiding in the hamper or swimming in the kitchen sink. Well, come to think of it, I might do those things but it's not the normal case.

    I don't object to carrying identifying items with me when I go out, but I just don't do it at home.
    _____________

  • People have already mentioned some of these, but I'll reiterate anyway :)

    1. Trainable room temperature, based on temperature outside & current temperature inside, time of day/year, and whether anybody is in the house or not (and possibly WHO is in the house), vents to individual rooms, cost. Simple training using remote to indicate currently where too hot or too cold & measurement of fuel/electricity use, with some factors to make the neural net understand that temperature change is not instant.

    2. Trainable lighting - based on light coming in from outside and/or time of day/year, and whether somebody is in the house/room (and possibly who is in the house/room) and whether or not there are other independently-controlled sources of light, & electricity cost. Possibly hook up with automated window blinds, to control light from outside (perhaps also a privacy factor). Similar training mechanism as for heating/cooling (too bright/too dark/electricity cost).

    3. Trainable water temperature & amount (depends on which faucet (kitchen/bathroom/shower/tub/etc), who is asking, time of day/year, competition for water sources, how much water is left in the hot water heater, cost. Train by hot/cold/too much/too little/cost.

    4. Home entertainment (at least volume for stereo, based on where listener is located & time of day). Could also be choice of station, both for radio & TV, although I'm sure the neural net would end up getting "punished" regularly :)

    5. Security - choose reaction (turn on more sensors, turn on fake dog barking, turn on surveillance, turn on siren, alert police, alert owner, etc) based on which combinations of sensors are triggered. Send the robot with the gun? Training this net could be fun :)

    I'm sure people will be able to think of plenty more - question is, will they be simple enough to implement?
  • Bill Gates' book, I belive it was called "The Road Ahead", which was published quite a few years back (around the Win 3.11 days) contained a CD with a "virtual tour" of the future Gate's mansion which outlined the various innovations the home would have, which I must say, were rather impressive. The things I can remember right off the top of my head were a tracking badge you would clip on when you enter the house, which would allow music to follow you around, art (displayed on wall-mounted flatscreen monitors) would change to match things you like, and phone calls would be routed so that only the phone nearest to you would ring. I'm not sure, but I think I recall it mentioning temps and lights adjusting to fit your prefrences, though I am not sure... If anybody wants, I'll dig up the CD and see if I can get more specific information.
    -Dan
  • Back propogation isn't the only way to teach a neural net. There's plenty of ways you can set up the system to teach itself a function. Temporal difference [ibm.com] learning is one such way that uses back propogation to manipulate the network weights but generates its own internal error signal without any external teacher. It takes a lot longer to learn the function but it can be done.
  • They don't learn like humans do, but a (three layer) neural net can express *any* function. That is, if you have a finite number of combinations of inputs and outputs and you don't have the answers for each one, you can enter the ones you know and extrapolate from there. In this case there are not many possible combinations for the lights, etc. so the results should be reasonable. Neural nets have been successfully used for face and handwriitng recognition, which are hardly trivial. Neural nets are useful when you need results more or less immediately but the system can improve as you go along and get more examples.

  • The Xerox PARC crowd fooled around with something like this a decade ago, but it wasn't very useful in office environments.

    Adaptive room control would probably be most useful for conference rooms and lecture halls. Lighting, HVAC, blinds, sound systems, and microphones all need to be coordinated, and it's usually done badly unless there's an operator for all the stuff. There, you might have a system using motion detectors and maybe a TV camera to distinguish between "room is empty", "a few people are in the room", "room is full", and "room is overcrowded", along with "writing on board", "using projector", "sun streaming through windows onto screen", etc.

    Most of the smarts is needed to figure out what the room situation is from the sensors. What to do is mostly a mode thing.

  • A house of this cost would have much wider water pipes than the standard american pipes and the water pressure would not be a problem.
  • First, it is a misconception to think that the back propagation-model is the only type of neural network, there are many more! There are also several types of models that do not need any 'external program' to modify there behaviour (for example Interactive activation).
    Second, the fact that usually an algorithm is being used in backprop is not so much because the model can't do without, but because this is the easiest way (for now) to implement this subtask. The idea op backpropagation IS part of the model and may or may not be part of some implementation..

    cheers,
    DaBs

  • Did this make anyone else think of the Ray Bradbury story, "There Shall Come Soft Rains", about an automated house that outlives its owners, and keeps operating as if they were there?
    --
  • Use the same controls that people are familiar with and allow the house to learn from corrections that are made.

    The house would have heat control that considers the usage patterns and the outside weather. The house would detect motion to control which rooms are heated, lit, etc.

  • Though I don't think a Neural net is necessary, or necessarily useful in this case.

    There are lots of interim steps that you can take to make your house seem smarter. For example, at one well-publicized geekhouse in Santa Cruz, Darkwater (webpage seems to have gone missing), my friend Charlie (Creator of OmniRemote [pacificneotek.com] for Palm Devices (shameless plug) rigged up a system to make heating work for individual rooms. To wit, each room was fitted with its own digital thermostat, and a flap in the vent which was opened and closed via some sort of servo system. If any thermostat in the house wanted heat, then the heater kicked on (think of this as a big set of OR gates) and any room which wanted heat would open its vent.

    That's just one example; There are probably lots of things which could benefit from similar improvements, or at least similar applications of geek brainyness.

    If you DO decide to go the neural networks route (which is worth doing just for the geek/hack factor, IMO) then you're going to have to decide what criteria you want it to base its decisions on, how you're going to track all of that criteria, and what kind of sensors you're going to use for anything that is sense-based and not knowledge-based.

    For example, one poster has already suggested [slashdot.org] that the system learn from human intervention. They use turning on a light at 5:30 as an example. So you go and replace all your light switches with X10 devices, and you have some device which logs your X10 codes and feeds them into the neural net. But now you have to decide which pieces of information to add; As you've probably already figured out, this is the key to having this work well. You should track the day of week, though also tracking weekday/non-weekday has a great potential to help this feature learn to be useful more quickly.

    But that's not nearly enough data; There's also other useful things like "Am I present in the house", which might mean you want other devices turned on; You're going to have to have some default behaviors there. Or perhaps "is it Christmas morning", in which case you might want the lights already blazing before you get downstairs so that you don't go blind trying to adjust to the light levels before your morning coffee or penguin mints or whatever geeks consume for pep these days.

    The other things you should make sure of are that you can still live your life without the system, and that it doesn't get too uppity. If you make a change in state, you don't want it changing it back before you're done with that state change.

    And do yourself a favor, implement voice recognition, and make it make plain sense. Use an activation word or phrase; I recall some system (in a Niven book, maybe?) using "Prikazvyat" (sp?) which IIRC is Russian for "Command" or something. It's been a while. Giving the system a distinctive name is another fine idea; "Computer" is probably a poor choice. Don't worry about being able to issue commands in English, either. Having the computer recognize what you're saying 99% of the time is more important than flow of speech. Saying "Halloran, lights this room up full" is an acceptable compromise, and should be reasonably easy to recognize.

  • Suppose you have a dimmer switch, temperature gauge for your house etc.

    Wouldn't it be great if the neural network set the system to the right value BEFORE you asked it to?

    So the way it works is that everytime you change a setting, it assumes that you've changed it for a reason, so it tries to correlate its sensory inputs (time, outside temperature, inside temperature, humidity, infrared sensing of people, time of year, how dark it is outside etc. etc.) with what changes you've made.

    Then next time when its sensory state changes in that way it sets the outputs that way before you ask it to.

    Anyway that's the theory. And its a way cool theory in my opinion.

    There are lots of problems. Still, not having any hot water for a cool high tech reason is better than not having any hot water because you forgot to turn on the water heater ;-)
  • The question posed in this article really doesn't make much sense. Why do we want to see neural networks in our homes if we don't have an end-goal?

    I think most people live in such a way that intelligent-guessing of there habits is going to be more of a problem than simply giving them control of there environment through a 'stupid' network.

    For example, as many posters have mentioned here; the lights in your home. You can't *guess* when a person wants a light in a room on based on any number of variables, just the same as you can't go in to someone else's house and control there lighting for them without getting feedback from them; ie: "I want lights to turn on in all rooms I *may* enter, a light on in the room I am in (obviously) and lights to turn off behind me, in rooms I can not enter directly from the spot I am in". Well this type of processing requires only sensors; deciding on whether the person wants bright, medium or dim lights is based completely on how they feel at the moment and no neural network has the ability to predict that with even effective accuracy.

    Other examples of house-hold tasks that do not require a neural network: Toilet Flushing Heat (stupid networks control heat better) Water from taps Bathtubs filling at specific times Windows automatically tinting for heat-retention Dishwashing Laundry

    etc. A neural network is meant to bridge a gap between people's simple requirements, and complicated digital processing. There is no requirement for digital decisions that are literally, "on" or "off".

  • I can see a house that is intelligent. Star Trek, and all that. That could be useful, fun, etc.

    But what I do not want is the intermediate levels of intelligence.

    For example, would I want a house as intelligent as a puppy or a parrot?

    This gets into matters of personality, etc. Most usable modules would likely not have any viable personality, because otherwise we would have to much independance and possible arguements, and other things that are quite maddening.

    I do not want to live in the 21st century equivalent of a Monty Python skit.

    All this aside, I would see that a nueral net would be useful for learning to automatically adjust things like heat and air conditioning. Security may be okay, but I've seen too many movies to trust them with things like weapons and other defensive measures.

    ;-)

  • They bug me because it seems like a gratuitous use of technology. Believe me, I'm all for technology, but I think we should use it where it fits, not go nuts-blind with it. I feel (just a feeling) that trying to make our homes too smart is rather wrong-headed.

    For example:

    Heating control. Personally, I don't want to walk into a room and be surprised that it's ten degrees colder (or ten degrees hotter) because the A.I. failed to predict that I'll go there. I would prefer to tell the computer not to condition the air in certain rooms, possibly at certain times of the day or days of the week. Good old fashioned programming (with possibly something simple like fuzzy logic) will suffice. The real problem is making an intuitive user interface that a layman can use to program it.

    Lighting control. Again, I don't think this makes sense, because lighting is far more dynamic. I want the lights on where I am, not where the computer thinks I want to go. It's a control problem, pure and simple. Just install sensors that read where I am, and control the lights directly. (Of course, sometimes I might want to override it.)

    Central music control. This one is the most dynamic of all. Not only does it depend on where I am, but how I feel. There are neural networks that can verge on reading facial expressions these days, but I would find it rather creepy and annoying if the house started piping in music to try and cheer me up, or try and fit my mood. My feeling is that music selection is a database access problem, not an A.I. problem. You want to be able to choose what you want quickly; you don't need a computer to try and predict or intuit.

    At the heart of it, I think my problem with the whole idea is this: I want control over my house. The A.I. of today is not intelligent enough to be useful. It would need to have almost human intelligence to be useful, and I believe that by the time computers are that smart, we'll be able to plunk them into robotic bodies, bypassing this whole question.

    Places where neural networks might be useful are in low-level control systems for complex machinery, like the furnace, the water heater, or the plumbing. These would not constitute neural network control of a house, but rather the underlying subsystem.

    --

  • But what if I don't want to constantly monitor what my house is doing to 'teach it'. Sure if the TV turned on and I didn't want it on I could turn it off, but isn't that like having a three-year old running around that you have to constantly monitor. I can barely take care of my plants.
  • How would the owner know if the house has adapted?
  • 1. The initial learning curve for the house would be months. I prefer to spend my time doing other things than teaching my house what temperature I like my baths, what level of brightness I like the lights in my living room at 5:00pm compared to 10:00pm, etc. 2. Exceptions are even harder to get programmed in in a short period of time. I'd hate to plan a romantic Valentine's Day with a candlelit dinner to suddenly have the TV kick on to Babylon 5 and all the lights switch to blue.
  • If it's to be revolutionary, it needs heat sensors to detect your body temperature and adjust the A/C or heater according to the preset temperature you have specified. Of course that idea is well suited for an individual. Multiple family members may be a little complex, especially if they have different comfort zones. Maybe an ID tag of some sort, but it would be nice to track individuals in other ways.

    For lighting, it would be nice to tell if you are coming from a room that has had the lights off, such as waking in the middle of the night. In that scenario, it would be nice to have lights come on automatically but be dim. Maybe if a person needs to be waking during the night hours for an early job, allowing the programming to gradually increase the brightness as the person wakes up would be a nice feature.

    The real trick would be a simple way to do train the neural network. I'm not sure what would be best, but a simple method would definitely be a good idea, even if the individual only has to go through the process once, they won't use it if it's too complex to program. I know several people that have security systems but don't use them because they don't feel like learning the interface.
  • I'd recommend using some sort of hybrid system of neural networks techniques and fuzzy logic. In fact, there's no reason not to regard a fuzzy logic system as a neural network...

    And even those may be too exotic for what you're trying to accomplish. How many sensors and the like are you thinking of working with? Unless you plan to monitor enormous amounts of environmental data (temperature, humidity, light, and motion in every room at a bare minimum), your system is doomed to being relatively "stupid" anyway. But back to the point...

    A fuzzy expert system would be an easy way to build the base of an "intelligent" house controller, by establishing simple variables and rules (a la "if KITCHEN-LIGHT-LEVEL is LOW then KITCHEN-LIGHT is ON-FULL" etc). This is easy to establish initially, and gives you an "out of box" working system. Some sort of feedback technique (a la back-propagation, but modified to fit what you're trying to accomplish) can be used then with the "good/bad" remote mentioned above. Basically, you have two things you can tweak iteratively when "training" the system in this kind of a case. You could lower the weight that certain rules have, or you can modify fuzzy variable definitions (what exactly is a "LOW" LIGHT-LEVEL? maybe it's even specifically, what is a LOW KITCHEN-LIGHT-LEVEL?).

    I think the idea is very workable, although I'm not sure how terrific it'd work IRL. Make sure to include an automatic override! (No, dammit, I know I'm not moving. That's because I'm READING...)

    "I'm sorry, I can't do that..."



  • Forget neural networks, what people want is a Rosie the Robot [inficad.com] for their homes.

  • A wonderful problem, a disappointing problem. (Score:3)

    by mosch ( 204 ) on Saturday January 06, 2001 @05:48PM (#526366) Homepage
    There are two problems with this discussion, one is wonderful. I'm making an attempt to identify them in the hopes that one or two more people might post intelligently and inspire some good ideas and responses.

    The first problem is wonderful. The question that's been posed to us is vague, perhaps purposefully vague. It talks of "neural networks" without a stated problem. Is Hougaard looking for a way to run his heat and air conditioning? Does he want lights to automatically do what he'd like them to do? Does he want his house to predict what kind of music he'd likely enjoy at a certain point, and play it? This lack of definition seems to have stumped most respondants.

    The second problem is a lack of informed, creative response. This is slashdot, a place where people like to think they have a better grasp on technology and it's implications than the rest of the world. This discussion is proving that it isn't so. Where's the creativity? Why are there posts which don't seem to indicate any hint of knowledge about how neural networks work?

    I think this is a wonderful, amazing idea. Imagine if you will, starting small. Take one thing, for the first item, I'll pick air conditioning and heat. The system is set up such that in each room, there's a method of indicating if it is too hot, or too cold. The system could contain a clock, a basic weather station with access to humidity, temperature, wind speed and direction.

    After a little bit, one could have a system which knows that if the wind has kicked up from the south, then the master bedroom starts to feel a little bit cold, but the rest of the house will be the same as usual. It will know that you tend to watch TV in the family room, which isn't over a basement, and thus gets a cold floor when the temperature has been below 50 for more than a few days. These are the kind of optimizations that would take forever to program into standard logic.

    As a more interesting, harder to get right example, music. Let's say you have a centralized database of music, with automated access to your CD players, your mp3 database, and Music Choice on your satellite TV. That part's easy, I've got that. I also categorized all my music, no matter what the format is, and I'm sure I'm not the only one. After all, it's a hell of a lot easier to buy a stack of 200 CD changers, and write some software to control them, than it is to remember where it was you decided to file that Negativland cd, or that orchestral recording with Brahms and Rachmaninov on the same CD.

    Now all we do is modify that software, to help the neural network understand what it is we're likely to want to hear at any given time. If I've been sitting at my unix box working (detectable by the state of xscreensaver), then I'm probably coding. Because I've manually picked the same genre of music every other time I've been activating these neurons, it puts on the new Dark Soho album, and I find myself listening to some slammin' trance. If it guessed wrong, well I just go to the standard music interface, tell it 'no, i wanted to listen to that midfield general ep i finally picked up' and eventually it figures out 'hey, this guy overrides his standard preferences, for stuff that's new to my database.' It might not get it right every time, but it'll likely be a hell of a lot better than what I'd get if I just put the player on random.

    Surely somebody in this crowd of self-proclaimed geeks and cutting-edge thought, can realize the potential of this, and open your mind to the possibilities of a system like this. Possibilities like incredible profit. Ludicrously incredible profit.

    Stop whining about what isn't possible, and think about what is! It's the 21st century, and if I can't have a rocket pack and a flying car, I want a house that plays dope tracks, automatically.

    --
    "Don't trolls get tired?"

  • Two issues (Score:3)

    by maggard ( 5579 ) <michael@michaelmaggard.com> on Saturday January 06, 2001 @03:29PM (#526367) Homepage Journal
    I think you're confusing two issues here:

    1. "Smart Homes" that have intelligent appliances or other otherwise control their internal systems in a way more high-tech then the traditional discrete switches on the wall & the occasional independent light/water/etc-sensor & timers.
    2. Neural Nets as a programming tool (method? algorithm? model?) vs. other more traditional explicit systems like cause/effect rules & preset series of grouped functions ("Party Mode", "Bedtime Mode", etc.)

    Combining them is interesting but first you've got to find someone who has a "Smart House" then discover if they use "Neural Nets" in any way. Even on /. the number of folks who live in full-blown (or even partial) smart homes is incredibly small and with that small sample the odds of finding someone using neural nets is even more remote.

    Consider posting on home.automation newsgroups, dedicated websites, and mailing-lists. There at least you'll have reached the first criteria of your study and can begin looking for the second.

    I also wonder why neural nets would make any difference? Are you interested in systems that can 'learn' from an occupant? Are you looking to compare 'nets to other more traditional systems using sensors & statistics? Comparing different types of 'nets against each-other? Identifying learning-curves, ability to respond to differing situations, appropriateness of responses? How could one even evaluate "success" or "accuracy" against other automation systems? (Yes I know there are methods even for very fuzzy stuff like this but I can't imagine a sample-set out there being large enough to be meaningful.)

    Not to be disparaging but unless your posting has been edited-to-idiocy it appears overly broad & extremely vague. Indeed what applicability any of this has to architecture escapes me. Systems Engineering, Electro-Mechanical Engineering, Artificial Intelligence, Human Interfaces: Yes but all of these are the provenance of specialists, not Architects (at least amongst the architectural curriculum I'm aware of.)

    Or is this simply combining two hot buzzwords in a way to create a research project out of thin air?

  • I've got it (Score:3)

    by nomadic ( 141991 ) <`nomadicworld' `at' `gmail.com'> on Saturday January 06, 2001 @07:40PM (#526368) Homepage
    This would make it great for pranks; sneak into someone's house and then train the network to play the theme from Psycho whenever someone takes a shower...
    --

  • I don't think it would be a good idea (Score:5)

    by Flavio ( 12072 ) on Saturday January 06, 2001 @02:54PM (#526369)
    Neural nets usually work well in areas where conventional binary logic fails. Text, image and speech recognition are examples.

    A neural net in your home would, in my opinion, be too complex to bother with. Neural nets are self programmed through experience to perform choices that aren't easy to define in computer code.

    For example, some time ago there was this slasdot post about a program which supposedly recognizes "innapropriate" images (i.e., porn). It can be used in web proxies, for example. The program didn't perform very well (in my opinion, it failed miserably, as the task is extremely difficult).

    A very complex neural net could theoretically learn from experience to recognize the difference between a naked baby and two people having sex. You can't program such a net by hand because there are so many neurons involved and influencing other neurons in ways so complex you can't even imagine.

    Now why would you want to use that to switch/dim lights in a house? The net could learn your behavior through experience at first, for example. It could have this "learn mode", much like smart network switches do. The net itself would be useless at this point, and it would record what you do at particular times of the day and perhaps make notes on your moods and act accordingly. After this learning period it would do things on itself and be corrected if the choice was incorrect. But hey, I really don't think you need the black magic that neurons give you to notice that.

    The bottom line is that people are usually very predictable. Neural nets are great when nuances from an objective POV are fundamental (like position/density of beige colors in an image as an indicator of porn) and this doesn't seem to be the case.

    Flavio

  • neural-network wants (Score:5)

    by buss_error ( 142273 ) on Saturday January 06, 2001 @03:09PM (#526370) Homepage Journal

    I want one that uses a pnumatic ram to toss salesmen off my property, after they ignore the 8"x11" NO SOLICITING THIS MEANS YOU sign.

    One that can sense when I bring a visitor home and clean up real quick.

    One that uses a deep booming voice to say "THAT SCUM IS SCAMMING YOU!" when the A/C repairman says my unit will colapse into dust in four seconds, posining my family and pets.

    I want one that will project a hologram of Satan when Jehova's witnesses come around, or one of an avenging angel when satanist's come knocking.

    One that will order booze when I'm low and send the bill to M$.

    One with a radio control unit built in to mow the lawn.

    Scans my e-mail and ZOT's spammers, then delete the e-mail.

    Seriously, I don't know the relm of possibility with neural-networks. Haven't looked at 'em, don't know what's possible and what isn't. Guess I need to start looking around for info....

Slashdot Top Deals

"No matter where you go, there you are..." -- Buckaroo Banzai

Close