AI Neural Networks based Prediciton

kulls has asked for the wisdom of the Perl Monks concerning the following question:

Replies are listed 'Best First'.
Re: AI Neural Networks based Prediciton by GotToBTru (Prior) on Sep 16, 2014 at 14:29 UTC
Google says AI::NeuralNet::Simple. Looks like a place to start. 1 Peter 4:10	[reply]
Re^2: AI Neural Networks based Prediciton by kulls (Hermit) on Sep 16, 2014 at 18:08 UTC
Hi, Thanks, I am bit confused how to train my neurons ( trained sets ) as my stock details are single stacked column and what would I suggest as output ? All examples are descibing XOR where output is defined whereas I want to predict the data for a given input data. Please suggest me on this Raja K	[reply]
Re^3: AI Neural Networks based Prediciton by GotToBTru (Prior) on Sep 16, 2014 at 19:58 UTC
You need to define what output you want for a given input. You train the neural network by supplying both the input and the output, and it makes the internal adjustments to produce those results. In the examples, they provide 0 and 1 as input, and expect 1 as output, and 1 and 1 as input, and expect 0 as output. That's what an XOR does. You need to define a set of inputs and the output you expect in each case. That is what you will use to train your neural network. 1 Peter 4:10	[reply]
Re^4: AI Neural Networks based Prediciton by kulls (Hermit) on Sep 17, 2014 at 08:56 UTC
Re^5: AI Neural Networks based Prediciton by Corion (Patriarch) on Sep 17, 2014 at 09:03 UTC
Some notes below your chosen depth have not been shown here