Make encoders probeable on ensembles

[tbekolay]

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).

[bmorcos]

Once encoders are probeable directly from the ensembles do we want to keep encoders probeable from the learning rule as well or remove that?

Encoders probeable from ensemble & learning rule
Encoders probeable from only ensemble

[drasmuss]

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.

[shrutisneha2011]

how can we check the synaptic weights in nengo @drasmuss kindly reply

[drasmuss]

Hi @shrutisneha2011. The best way to get help with modelling questions is to post them on https://forum.nengo.ai/

[shrutisneha2011]

Thank you so much Sir for your reply. It really means a lot, i tried so far
reaching you but failed.

On Mon, Sep 12, 2016 at 5:48 PM, Daniel Rasmussen notifications@github.com
wrote:

Hi @shrutisneha2011 https://github.com/shrutisneha2011. The best way to
get help with modelling questions is to post them on
https://forum.nengo.ai/

—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
#1117 (comment), or mute
the thread
https://github.com/notifications/unsubscribe-auth/AQ_ZbmpHqzxzITvvim5amu-3qwgNjssxks5qpUMOgaJpZM4JEQ1I
.