HackerPapers

arXiv:1611.05141cs.NE

Training Spiking Deep Networks for Neuromorphic Hardware

Eric Hunsberger, Chris Eliasmith

Abstract

We describe a method to train spiking deep networks that can be run using leaky integrate-and-fire (LIF) neurons, achieving state-of-the-art results for spiking LIF networks on five datasets, including the large ImageNet ILSVRC-2012 benchmark. Our method for transforming deep artificial neural networks into spiking networks is scalable and works with a wide range of neural nonlinearities. We achieve these results by softening the neural response function, such that its derivative remains bounded, and by training the network with noise to provide robustness against the variability introduced by spikes. Our analysis shows that implementations of these networks on neuromorphic hardware will be many times more power-efficient than the equivalent non-spiking networks on traditional hardware.

arXiv comments
10 pages, 3 figures, 4 tables; the "methods" section of this article draws heavily on arXiv:1510.08829
Journal reference
DOI
doi:10.13140/RG.2.2.10967.06566
Subjects
cs.NENeural and Evolutionary Computing cs.LGMachine Learning

On Hacker News

Linked by 3 identifiable commenters in 3 comments across 2 threads, from Apr 2017 to Sep 2017.

Comments linking this paper, per year.

Discussed in comments2 threads

  1. Intel Introduces Neuromorphic Test Chip 1 comment

    • 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].…

      aurelian15View on HNParent context

  2. Stanford Brainstorm Chip to Hints at Neuromorphic Computing Future 2 comments

    • 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…

      Seanny123View on HNParent context

    • 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…

      p1eskView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.