Subject:
|
Those Silly AI programs (was: Design)
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Fri, 9 Dec 2005 04:21:24 GMT
|
Original-From:
|
dan miller <danbmil99@yahoo!saynotospam!.com>
|
Viewed:
|
1169 times
|
| |
|
|
My favorite:
A neural net was trained to recognize tanks. It worked perfectly on all the
test data, but failed completely on real data. To create the test data,
they shot pictures of some tanks, and some pictures of cars and other
non-tank vehicles in the same location. Turns out they did the tanks in the
morning, and the rest in the afternoon.
The network was looking at the color of the sky.
-dbm
--- steve <sjbaker1@airmail.net> wrote:
> danny staple wrote:
> > I do remember seeign something very similar to this during my studies,
> > except it was a genetic alogorithm based on rounds in an arena. The
> > genomes would gain fitness by being able to push their opponent out of
> > the ring. Some of the most sucessful were just vast blocks which would
> > just fall over.
>
> Another story like that - relating to neural networks - is of a busy
> Japanese subway system where they wanted to prevent overcrowding of
> platforms at the stations.
>
> The story goes that they planned to hook up a camera with a computer
> observing the station using a neural network algorithm in order to
> decide when to shut the turnstiles and prevent more people entering
> the platform.
>
> Training the system on photographs of full and empty platforms allowed
> the neural network to 'learn' a solution to their problem without anyone
> having to write tedious image processing software.
>
> The system went into operation and worked perfectly for many months
> until on a public holiday - it unaccountably locked the turnstiles
> when there was hardly anyone standing on the platform.
>
> After much careful analysis of the resulting neural net, they discovered
> that rather than triggering when there were too many people present,
> the neural net had learned how to read the clock on the wall opposite
> the camera - and was in fact shutting the doors at the same rush-hour
> times every day - regardless of the number of people on the platform!
>
> I don't recall where I heard this story - so it's very likely that I
> have some of the details wrong.
>
> However, it nicely illustrates the problems of learning/evolving
> systems.
>
|
|
Message has 1 Reply:
 | | Re: Those Silly AI programs (was: Design)
|
| (...) An interesting article on robotics and AI appeared in the FT today starting with "intelligent robots are here" or some such. The link is: (URL) is a Dan Millar who works (or used to) at Carnegie Mellon University -are you one and the same? Do (...) (19 years ago, 9-Dec-05, to lugnet.robotics)
|
Message is in Reply To:
| | Re: Design
|
| (...) Another story like that - relating to neural networks - is of a busy Japanese subway system where they wanted to prevent overcrowding of platforms at the stations. The story goes that they planned to hook up a camera with a computer observing (...) (19 years ago, 8-Dec-05, to lugnet.robotics)
|
6 Messages in This Thread:
 
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
This Message and its Replies on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
