New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Problem with random weights #20

Closed

jfvelezserrano opened this issue Oct 13, 2011 · 1 comment

Milestone

jfvelezserrano commented Oct 13, 2011

The random weights initialization doesn't work properly in version 3.0.1.

Follow this steeps to reproduce the problem:

Create a feedforward neural network.
Randomize the network using random [-1,1] values.
If you visualize the weight histogram you can observe that the weights follows a random distribution.
Train the network with some patterns.
Stop the training and close the training window.
Randomize again the network using random [-1,1] values.
If you visualize the weight histogram you can observe that the weights DOESN'T follow a random distribution.

ghost assigned seemasingh

Contributor

seemasingh commented Jan 26, 2012

Cannot currently reproduce this issue. Might have been an issue at one point, let me know if you still get this in Encog 3.1.

seemasingh closed this as completed

daydreamt mentioned this issue

testTemporal fails (and so does mvn package) #163

Closed

lasha81 mentioned this issue

problem with train.getError() #203

Closed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment