Inputs to neural nets, and 'remembering'

d000hg · 2004-09-12T00:50:40

Hello all, I've been reading a little on neural nets recently and while the general idea is ok (perhaps I could even write a simple net) one thing has particularly struck me this far - the inputs to the net. The tutorial at ai-junkie.com has an example for recognising the a number/character from an 8x8 matrix of pixels. They can be on or off and each pixel is mapped to one input to the net. Then each outcome has one output ie 26 for each letter and 10 for each numeral and you look to see which is the highest. But is it really the case you have one input per pixel in this fashion? If you wanted to look at a full-screen screen-shot that's of the order of 1Mpixels needing an input each. In fact since it's rgb you'd presumably need one for each channel of each pixel? Firstly this seems really expensive, and secondly it's very rigid and inflexible - what if you suddenly have a 800x599 image when before you only had 800x600? My other query is about a neural net remembering a state. I'm looking to use nets for a racing game, possibly. I read with interest the recent article about Colin McRae Rally 2 and I got thinking about the inputs there. You could have the car's orientation, speed, spin rate and information about the driving line at the point nearest the car, 5m furhter on and 30m further on for example. But the data supplied for training the net - was each frame of the game used as one data point - the state of the controls and these inputs mentioned were used to train the network? Firstly that seems a huge set of training data (60 points per second), but how good is that? Wouldn't you like the neural net to 'keep a thought in mind' and remember the last second rather than just take every game update in isolation to act upon? Do current neural nets have the concept of memory, or maintaining a state?

Artificial Intelligence Programming

Started by d000hg August 24, 2004 02:14 AM

20 comments, last by Vlion 20 years, 2 months ago

d000hg

Author

1,208

September 09, 2004 06:18 AM

Obviously not then!

Vlion

151

September 12, 2004 12:50 AM

1)
You'd want to transform your net and/or input so that it could handle missing points.

2)
Stateful neural nets are known as feed-back nets.
They are using for voice recognition, among other things.
Genetic algorithms are often used to train them.

~V'lionBugle4d

Inputs to neural nets, and 'remembering'

This topic is closed to new replies.

Popular Topics

Recommended Tutorials

Inputs to neural nets, and 'remembering'

This topic is closed to new replies.

Popular Topics

Recommended Tutorials

Reticulating splines