-
Notifications
You must be signed in to change notification settings - Fork 174
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.
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
Make encoders probeable on ensembles #1117
Comments
Once encoders are probeable directly from the ensembles do we want to keep encoders probeable from the learning rule as well or remove that?
|
I should mention, I implemented this for a different PR (#553, see commit 4a572c3). I just added probing to the ensemble (leaving the learning rule as is), but I think it'd probably make sense to remove it from the learning rule. I also didn't test that change at all, just tried it out for the specific use case in that PR. |
how can we check the synaptic weights in nengo @drasmuss kindly reply |
Hi @shrutisneha2011. The best way to get help with modelling questions is to post them on https://forum.nengo.ai/ |
Thank you so much Sir for your reply. It really means a lot, i tried so far On Mon, Sep 12, 2016 at 5:48 PM, Daniel Rasmussen notifications@github.com
|
Right now, to probe changing encoders, you probe a Voja learning rule object. However, since encoders 'belong' to ensembles, it makes more more sense to probe them on an ensemble rather than the learning rule. We should make it possible to probe encoders on ensembles (for the same reason we can probe the weights on connections).
The text was updated successfully, but these errors were encountered: