<div dir="ltr"><div><div><div><div><div><div>Hello all,<br><br></div>I recently got this book, listed here:<br><a href="http://www.amazon.com/Handbook-Neuroevolution-Through-Erlang-Gene/dp/1461444624">http://www.amazon.com/Handbook-Neuroevolution-Through-Erlang-Gene/dp/1461444624</a><br>
<br></div>The topic intrigues me, because it makes so much sense to try to design artificial <br>neural networks with Erlang (a point that the author makes very well in the book).<br><br></div>I got to chapter 6 and this is the code that I have for constructor.erl. Now, I'm going <br>
through the create_NeuroLayers/4 and... I don't see the connection between what's <br>written and artificial neural networks...<br><br></div>The code:<br><a href="http://bin.cakephp.org/view/1946842426">http://bin.cakephp.org/view/1946842426</a><br>
<br></div>I don't want to bash the author, but I'm really not "getting" what he's describing. For example, this description:<br><br>The function create_NeuroLayers/3 prepares the initial step before starting the recursive cre-<br>
ate_NeuroLayers/7 function which will create all the Neuron records. We first generate the<br>place holder Input Ids “Plus”(Input_IdPs), which are tuples composed of Ids and the vector<br>lengths of the incoming signals associated with them. The proper input_idps will have a weight [me: but we haven't assigned the weight, have we?]<br>
list in the tuple instead of the vector length. Because we are only building NNs each with only a<br>single Sensor and Actuator, the IdP to the first layer is composed of the single Sensor Id with<br>the vector length of its sensory signal, likewise in the case of the Actuator. We then generate<br>
unique ids for the neurons in the first layer, and drop into the recursive create_NeuroLayers/7<br>function.<br><br></div>Thanks in advance.<br></div>