Stochastic Computing Can Improve Upon Digital Spiking Neural Networks
Authors:
- Sean C. SmithsonSSSean C. Smithson
- Kaushik BogaKBKaushik Boga
- Arash ArdakaniAAArash Ardakani
- Brett H. MeyerBMBrett H. Meyer
- Warren J. GrossWGWarren J. Gross
- 1 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 309-314
Abstract
With the surge in popularity of machine learning algorithms, research has turned towards exploring novel computing architectures in order to increase performance while limiting power consumption. Inspired by their biological counterparts, digital spiking neural networks have emerged as energy efficient alternatives to conventional hardware implementations, yet remain largely incompatible with cutting edge learning methods. Representing information with single-bit binary pulse trains, the behaviour of spiking neural networks exhibit many interesting analogues to the existing field of stochastic computing. In this paper, we not only illustrate the parallels between digital spiking neural networks and stochastic computing, but we also demonstrate that many computing elements in modern spiking hardware are, in fact, implementations of stochastic circuits. In addition, we show that stochastic computing design techniques can be leveraged in order to address shortcomings in current spiking neural network architectures.Keywords
This publication has 20 references indexed in Scilit:
- TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic ChipIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015
- STRAUSS: Spectral Transform Use in Stochastic Circuit SynthesisIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015
- A million spiking-neuron integrated circuit with a scalable communication network and interfaceScience, 2014
- Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural SimulationsProceedings of the IEEE, 2014
- Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores2013
- Cognitive computing systems: Algorithms and applications for networks of neurosynaptic cores2013
- Speech recognition with deep recurrent neural networks2013
- Bridging the semantic gap: Emulating biological neuronal behaviors with simple digital neurons2013
- Which Model to Use for Cortical Spiking Neurons?IEEE Transactions on Neural Networks, 2004
- Stochastic neural computation. I. Computational elementsIEEE Transactions on Computers, 2001