Neural Networks In The Home? 154
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."
I can see it now.. (Score:1)
Re:Neural Networks can't learn. (Score:1)
What about traffic lights? (Score:1)
Re:Neural Networks can't learn. (Score:1)
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).
Re:Better Temperature Control! (Score:1)
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.
Re:There's no reason not to (Score:1)
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?
Re:Fuzzy Logic (Score:1)
>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.
Re:What about traffic lights? (Score:1)
What are you trying for? (Score:1)
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
Nutrual Nets are probably over kill. (Score:1)
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.
Re:Nutrual Nets are probably over kill. (Score:1)
Right now the program doesnt learn, you just have to rate the music while its playing. I gave it a
Re:Haven't you read skinner? (Score:1)
Re:Smart thermostat - no neural net required (Score:1)
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.
Didn't work (Score:1)
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.
--
Neural Networks are a Tool (Score:1)
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)
I alreadh have a neural network for this (Score:1)
Re:A REMOTE?? (Score:1)
the shower.....and be quiet enough to run in the middile of the night.
It's been done by Mike Mozer (Score:1)
MIT MediaLab (Score:1)
Prof. Mozer controls his house with Neural Nets (Score:1)
http://www.cs.colorado.edu/~mozer/house/
for the details.
World class application of machine learning.
-- Malcolm
Air conditioning (Score:1)
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
Re:What about traffic lights? (Score:1)
Re:What are you trying for? (Score:1)
Re:Better Temperature Control! (Score:1)
Re:Learning your Habits (Score:1)
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
Re:What are you trying for? (Score:1)
Re:Okay - sounds good to me... (Score:1)
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.
Re:What about traffic lights? (Score:1)
Re:Learning your Habits (Score:1)
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.)
Get some boxes (Score:1)
Re:House Training (Score:1)
Cheers,
Rick Kirkland
2001: A Home Automation Odyssey (Score:1)
[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
Slow learners (Score:1)
Smart thermostat (Score:1)
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.
Re:A wonderful problem, a disappointing problem. (Score:1)
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.
Fuzzy Logic (Score:1)
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
Re:Nigger Networks in the Home (Score:1)
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)
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].
Research at MIT (Score:1)
Other useful links can also be found at http://home-automation.org/
Reading Material for Research (Score:1)
Here's the Web site for the book [penguinputnam.com], and also Ray Kurzweil's site [kurzweiltech.com].
Moderate this UP (Score:1)
Neural vs. Fuzzy (Score:1)
Neural Network home projects (Score:1)
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.Smart Homes, neural nets (Score:1)
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.
Neither Can Fuzzy Logic System (Score:1)
Divide and conquer (Score:1)
What is the appeal of a `smart' house? (Score:1)
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.
Re:i hate to say this but (Score:1)
Re:Two issues (Score:1)
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??
Re:"Smart Elevator"? (Score:1)
Re:Any other examples? (Score:1)
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...
Re:Neural Networks can't learn. (Score:1)
> 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.
Neural Networks can't learn. (Score:1)
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.
Re:Neural Networks can't learn. (Score:1)
Have you heard about backpropagation learning for recurrent neural nets?
Re:Neural Networks can't learn. (Score:1)
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.
Re:intelligent houses (Score:1)
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.
Re:'Smart Homes' bug me (Score:1)
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 have one in my home (Score:1)
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
Re:i hate to say this but (Score:1)
---
Dr. Trevorkian
Re:Why a neural network? (Score:1)
---
Dr. Trevorkian
My home already has a neural net! (Score:1)
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.
"Smart Elevator"? (Score:1)
...
Yeah, that was pretty funny.
-------
What is a neural network? (Score:1)
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)
-57 Celsius (-70.6 Fahrenheit)
Wrong Tool (Score:2)
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.
Utility of Neural Nets (Score:2)
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.
Re:Two issues (Score:2)
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?
It's been done (Score:2)
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
Re:MIT MediaLab (Score:2)
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.
Re:Utility of Neural Nets (Score:2)
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
A REMOTE?? (Score:2)
Slight aside.. but AI related. (Score:2)
Fundamentally Doomed to Failure (Score:2)
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 ***
House Training (Score:2)
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?
Re:i hate to say this but (Score:2)
I don't object to carrying identifying items with me when I go out, but I just don't do it at home.
_____________
Possible house uses (Score:2)
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?
Re:i hate to say this but (Score:2)
-Dan
Re:Neural Networks can't learn. (Score:2)
Re:Neural Networks can't learn. (Score:2)
Work at PARC (Score:2)
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.
Re:A REMOTE?? (Score:2)
Neural Networks CAN learn! (Score:2)
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
hmmm (Score:2)
--
Don't instruct, let it observe (Score:2)
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.
There's no reason not to (Score:2)
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.
Yes, I know what Neural networks might do. (Score:2)
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
Neural Networks vs. Stupid Networks (Score:2)
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".
intelligent houses (Score:2)
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.
;-)
'Smart Homes' bug me (Score:2)
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.
--
Re:Not a problem (Score:2)
Re:Well.. (Score:2)
Some Problems (Score:2)
No remote. (Score:2)
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.
my take (Score:2)
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..."
That's what Rosie the Robot is for (Score:2)
Forget neural networks, what people want is a Rosie the Robot [inficad.com] for their homes.
A wonderful problem, a disappointing problem. (Score:3)
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)
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)
--
I don't think it would be a good idea (Score:5)
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)
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....