Online Few-Shot Gesture Learning on a Neuromorphic Processor

Online Few-Shot Gesture Learning on a Neuromorphic Processor

IEEE Journal on Emerging and Selected Topics in Circuits and Systems

10.1109/JETCAS.2020.3032058

https://ieeexplore.ieee.org/document/9229141

Kenneth Stewart, Garrick Orchard, Sumit Bam Shrestha, Emre Neftci

neuromorphic computing, spiking neural networks, on-chip learning, few-shot learning, online learning

19 October 2020

Stewart, Kenneth & Orchard, Garrick & Shrestha, Sumit & Neftci, Emre. (2020). Online Few-shot Gesture Learning on a Neuromorphic Processor.

We present the Surrogate-gradient Online Error-triggered Learning (SOEL) system for online few-shot learning on neuromorphic processors. The SOEL learning system uses a combination of transfer learning and principles of computational neuroscience and deep learning. We show that partially trained deep Spiking Neural Networks (SNNs) implemented on neuromorphic hardware can rapidly adapt online to new classes of data within a domain. SOEL updates trigger when an error occurs, enabling faster learning with fewer updates. Using gesture recognition as a case study, we show SOEL can be used for online few-shot learning of new classes of pre-recorded gesture data and rapid online learning of new gestures from data streamed live from a Dynamic Active-pixel Vision Sensor to an Intel Loihi neuromorphic research processor

PublisherCopyrights

This research / project is supported by the National Research Foundation - Advanced Manufacturing and Engineering Progammatic grant
Grant Reference no. : A1687b0033

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/17509

2156-3365

Institute for Infocomm Research