[nengo-user] About the model "RBM Deep Belief Network for Visual Digit Recognition"

[Eric Hunsberger]

Hi Zonghua,

In the ANN, each hidden unit is computing a sigmoid function. In the
spiking model, we use three LIF neurons to "decode" this sigmoid function
(using the principles of the NEF). Essentially, this means taking three LIF
neurons with random intercepts, and using them as regressors to fit the
sigmoid function.

Best,
Eric

On 25 March 2015 at 02:43, Zonghua Gu <zonghua at gmail.com> wrote:

> We built a FPGA for simulation of Spiking NN, and are looking for
> models as test applications. We hope to use the digit recognition
> example here http://models.nengo.ca/node/28. But from reading the
> paper, and the provided digit.py file:
>
> Tang Y, Eliasmith C. Deep networks for robust visual
> recognition[C]//Proceedings of the 27th International Conference on
> Machine Learning (ICML-10). 2010: 1055-1062.
>
> It seems it is not a spiking neural network. But the documentation
> says "A spiking neuron model for digit recognition, created by
> training an RBM Deep Belief Network on the MNIST database, then
> converting the resulting model to spiking neurons via Nengo." Could
> you please explain how the conversion is done?
>
>
> --
> Zonghua Gu
> Zhejiang University
> _______________________________________________
> nengo-user mailing list
> nengo-user at ctnsrv.uwaterloo.ca
> http://ctnsrv.uwaterloo.ca/mailman/listinfo/nengo-user
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://artsservices.uwaterloo.ca/pipermail/nengo-user/attachments/20150325/2e2b2826/attachment-0002.html>