An error-propagation spiking neural network compatible with neuromorphic processors

Spiking neural networks have shown great promise for the design of low-power sensory-processing and edge-computing hardware platforms. However, implementing on-chip learning algorithms on such architectures is still an open challenge, especially for multi-layer networks that rely on the back-propaga...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Cartiglia, Matteo, Haessig, Germain, Indiveri, Giacomo
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 12.04.2021
Subjects
Algorithms
Analog circuits
Approximation
Auditory perception
Back propagation
Back propagation networks
Circuit design
Computer architecture
Edge computing
Error signals
Machine learning
Multilayers
Neural networks
Power management
Propagation
Signal processing
Spikes
Spiking
Weight
Online AccessGet full text

Cover

More Information
Summary:Spiking neural networks have shown great promise for the design of low-power sensory-processing and edge-computing hardware platforms. However, implementing on-chip learning algorithms on such architectures is still an open challenge, especially for multi-layer networks that rely on the back-propagation algorithm. In this paper, we present a spike-based learning method that approximates back-propagation using local weight update mechanisms and which is compatible with mixed-signal analog/digital neuromorphic circuits. We introduce a network architecture that enables synaptic weight update mechanisms to back-propagate error signals across layers and present a network that can be trained to distinguish between two spike-based patterns that have identical mean firing rates, but different spike-timings. This work represents a first step towards the design of ultra-low power mixed-signal neuromorphic processing systems with on-chip learning circuits that can be trained to recognize different spatio-temporal patterns of spiking activity (e.g. produced by event-based vision or auditory sensors).
ISSN:2331-8422