This is an efficient implementation of a fully connected neural network in NumPy. The network can be trained by a variety of learning algorithms: backpropagation, resilient backpropagation and scaled conjugate gradient learning. The network has been developed with PYPY in mind.
BSD 2-Clause "Simplified" License
297
stars
98
forks
source link
Wrong error assignment in resilient backpropagation #8
On line 230 in resilient_backpropagation you assign,
error = error
, I believe it should beprev_error = error