Training Spiking Deep Networks for Neuromorphic Hardware · HackerPapers discussions

Training Spiking Deep Networks for Neuromorphic Hardware — mentioned by aurelian15

Mon, 25 Sep 2017 23:11:18 GMT

There are several frameworks for the construction of spiking neural networks given an abstract mathematical description of the desired function. The most complete (note that I'm currently a student in the lab that developed this method) is the Neural Engineering Framework [1]. There is a Python reference implementation called Nengo [2] which can target several backends, including neuromorphic hardware. Training deep spiking neural networks is possible as well [3]. [1] http://compneuro.uwaterloo.ca/research/nef.html [2] https://www.nengo.ai/ [3] https://arxiv.org/abs/1611.05141

Paper and discussion history. A mention is not an endorsement.

Training Spiking Deep Networks for Neuromorphic Hardware — mentioned by p1esk

Tue, 11 Apr 2017 18:10:02 GMT

Hi Sean, perhaps you can help us understand the claim that analog hardware SNNs are more energy efficient than analog hardware non-spiking networks (e.g. based on floating gate transistors [1])? Also, in the paper [2], Table 4 is a bit confusing: what is the "traditional hardware" they're referring to? Finally, it's not clear from that paper, or from this "Brainstorm" article, that you actually have a working chip, capable of running Alexnet. Is that so? What is the current status of the actual hardware? [1] https://arxiv.org/abs/1610.02091 [2] https://arxiv.org/abs/1611.05141

Paper and discussion history. A mention is not an endorsement.

Training Spiking Deep Networks for Neuromorphic Hardware — mentioned by Seanny123

Tue, 11 Apr 2017 04:28:47 GMT

I'm from the lab working on this platform. A lot of people in this thread are claiming that there is no use for these spiking neural nets and I have to disagree. Brainstorm can run Spaun, the world's largest functioning and behaving brain model. [1] It can also run Adaptive Control circuits, which lead to unprecedented adaptability in arm control to undefined forces, such as changes in arm length, medium the arm is acting in and weights applied to the arm. [2] For an overview of how programming with spiking neural networks is different than normal programming, see this blog post I wrote…

Paper and discussion history. A mention is not an endorsement.