Hi,
I want to use the neural network package AMORE and I don't find in the
documentation the weight decay option.
Could someone tell if it is possible to add a regularization parameter (also
known as a weight decay) to the training method.
Is it possible to alter the gradient descent rule for
Hi,
I would like to generate a list of all subsequence of length k from an array
with length n (k < n). The result should be organized in a matrix.
So the matrix should look like the following whereas each row is one of a
subsequence of len k.
[a[1:k],
a[2:(k+1)]
a[3:(k+2)]
...
a[(n-k+1):
2 matches
Mail list logo