Event-Driven Signal Processing with Neuromorphic Computing Systems

Neuromorphic hardware has long promised to provide power advantages by leveraging the kind of event-driven, temporally sparse computation observed in biological neural systems. Only recently, however, has this hardware been developed to a point that allows for general purpose AI programming. In this paper, we provide an overview of tools and methods for building applications that run on neuromorphic computing devices. We then discuss reasons for observed efficiency gains in neuromorphic systems, and provide a concrete illustration of these gains by comparing conventional and neuromorphic implementations of a keyword spotting system trained on the widely used Speech Commands dataset. We show that replacing floating point operations in a conventional neural network with synaptic operations in a spiking neural network results in a roughly 4x energy reduction, with minimal performance loss.

[1]  David A. Patterson,et al.  In-datacenter performance analysis of a tensor processing unit , 2017, 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA).

[2]  Chris Eliasmith,et al.  A Spike in Performance: Training Hybrid-Spiking Neural Networks with Quantized Activation Functions , 2020, ArXiv.

[3]  Steve Furber,et al.  SpiNNaker 2: A 10 Million Core Processor System for Brain Simulation and Machine Learning , 2019, ArXiv.

[4]  Tara N. Sainath,et al.  Convolutional neural networks for small-footprint keyword spotting , 2015, INTERSPEECH.

[5]  Daniel Rasmussen,et al.  NengoDL: Combining Deep Learning and Neuromorphic Modelling Methods , 2018, Neuroinformatics.

[6]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[7]  Steve B. Furber,et al.  The SpiNNaker Project , 2014, Proceedings of the IEEE.

[8]  Hong Wang,et al.  Loihi: A Neuromorphic Manycore Processor with On-Chip Learning , 2018, IEEE Micro.

[9]  Sander M. Bohte,et al.  Error-backpropagation in temporally encoded networks of spiking neurons , 2000, Neurocomputing.

[10]  Trevor Bekolay,et al.  Nengo: a Python tool for building large-scale functional brain models , 2014, Front. Neuroinform..

[11]  Peter Blouw,et al.  Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware , 2018, NICE '19.

[12]  Garrick Orchard,et al.  SLAYER: Spike Layer Error Reassignment in Time , 2018, NeurIPS.

[13]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[14]  Pierre Yger,et al.  PyNN: A Common Interface for Neuronal Network Simulators , 2008, Front. Neuroinform..

[15]  Chris Eliasmith,et al.  Training Spiking Deep Networks for Neuromorphic Hardware , 2016, ArXiv.

[16]  Pete Warden,et al.  Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition , 2018, ArXiv.

[17]  Kwabena Boahen,et al.  Braindrop: A Mixed-Signal Neuromorphic Architecture With a Dynamical Systems-Based Programming Model , 2019, Proceedings of the IEEE.

[18]  Yundong Zhang,et al.  Hello Edge: Keyword Spotting on Microcontrollers , 2017, ArXiv.

[19]  Georg Heigold,et al.  Small-footprint keyword spotting using deep neural networks , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).