I'm a new at the cellular neural network, which is a special case of the recurrent neural network: my questions are: I understand the implementation of Chua circuit for the CNN, but I still need to

1- understand intuitively why every cell in CNN receives a summation of the outputs from the surrounding cells? mathematically it is clear how to analysis it but I'm talking about the idea behind that. 2- When do we decide to change the elements of matrix A and B or one of them, since some papers they set matrix B to zeros and sometimes matrix A to zero? I know they want to reduce the error but there is something still not clear. 3-I want to use CNN to classify images and I'm looking to a good reference to do that.

Thank you in advance,

  • $\begingroup$ this is not really clearly written, what matrixes are you talking about? plz edit to clarify $\endgroup$ – vzn Nov 28 '14 at 22:50
  • $\begingroup$ Matrix A in all papers means feedback weight matrix, but matrix B is the feedforward weight matrix. $\endgroup$ – Rosa della vita Nov 30 '14 at 2:39

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.