Answer by darkcanuck for TD(λ) in Delphi/Pascal (Temporal Difference Learning)
If you're serious about making this work, then understanding TD-lambda would be very helpful. Sutton and Barto's book, "Reinforcement Learning" is available for free in HTML format and covers this...
View ArticleAnswer by darkcanuck for java simple neural network setup
It looks like a good starting point. I do have a few suggestions:For scalability, fire() should be restructured so that a neuron that's already fired with the current input set doesn't have to...
View ArticleAnswer by darkcanuck for Neural Network Always Produces Same/Similar Outputs...
Based on your comments, I'd agree with @finnw that you have a bias problem. You should treat the bias as a constant "1" (or -1 if you prefer) input to each neuron. Each neuron will also have its own...
View ArticleAnswer by darkcanuck for Connect 4 with neural network: evaluation of draft +...
I've implemented neural networks before, and see a few problems with your proposed architecture:A typical multi-layer network has connections from every input node to every hidden node, and from every...
View ArticleComment by darkcanuck on Can you help me with linear activation of my Simple...
I would recommend both. For regression you also can use sigmoid/tanh activation in the hidden layer since it adds non-linearity to the function approximation. For the output layer I would normally pick...
View Article
