After convolutional layer base implementation issue being resolved, feedforwarding function and backpropagating function are left to be given shape to. feedForward() will produce activation by computing product between weight and input pixels within kernel range. backPropagate() would compute current error using next error and weight matrix. Convolutional layer unit test file will be added, too.
beomyeol
commented
8 years ago
After convolutional layer base implementation issue being resolved, feedforwarding function and backpropagating function are left to be given shape to.
feedForward()will produce activation by computing product between weight and input pixels within kernel range.backPropagate()would compute current error using next error and weight matrix. Convolutional layer unit test file will be added, too.