[nengo-user] About MNIST classification with DBN

[Sam]

I found these two versions of Deep Belief Network for MNIST digit
recognition. How are they related? It seems to me, one is based on spiking
NN, one is based on non-spiking classic ANN. Is my understanding correct?
https://github.com/hunse/mnist-rbm
http://models.nengo.ca/node/28

The non-spiking version should be based on this paper:
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.

But the spiking version has no references. Is it related to this paper?
O'Connor P, Neil D, Liu S C, et al. Real-time classification and sensor
fusion with a spiking deep belief network[J]. Frontiers in neuroscience,
2013, 7.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://artsservices.uwaterloo.ca/pipermail/nengo-user/attachments/20150325/981a6a3d/attachment-0002.html>