Event-Driven Intrinsic Plasticity for Spiking Convolutional Neural Networks

The biologically discovered intrinsic plasticity (IP) learning rule, which changes the intrinsic excitability of an individual neuron by adaptively turning the firing threshold, has been shown to be crucial for efficient information processing. However, this learning rule needs extra time for updati...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2022-05, Vol.33 (5), p.1986-1995
Main Authors: Zhang, Anguo, Li, Xiumin, Gao, Yueming, Niu, Yuzhen
Format: Article
Language:English
Subjects:
Artificial neural networks
Biological neural networks
Biological system modeling
Biomembranes
Brain - physiology
Computational modeling
Computational neuroscience
Data processing
Encoding
Energy consumption
Event-driven intrinsic plasticity (IP)
Excitability
Firing pattern
Information processing
input-driven IP
IP networks
Learning
Neural coding
Neural networks
Neural Networks, Computer
Neural plasticity
Neurons
Neurons - physiology
Plastic properties
Plasticity
Recognition
Recognition, Psychology
self-driven IP
Spiking
spiking neural network (SNN)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The biologically discovered intrinsic plasticity (IP) learning rule, which changes the intrinsic excitability of an individual neuron by adaptively turning the firing threshold, has been shown to be crucial for efficient information processing. However, this learning rule needs extra time for updating operations at each step, causing extra energy consumption and reducing the computational efficiency. The event-driven or spike-based coding strategy of spiking neural networks (SNNs), i.e., neurons will only be active if driven by continuous spiking trains, employs all-or-none pulses (spikes) to transmit information, contributing to sparseness in neuron activations. In this article, we propose two event-driven IP learning rules, namely, input-driven and self-driven IP, based on basic IP learning. Input-driven means that IP updating occurs only when the neuron receives spiking inputs from its presynaptic neurons, whereas self-driven means that IP updating only occurs when the neuron generates a spike. A spiking convolutional neural network (SCNN) is developed based on the ANN2SNN conversion method, i.e., converting a well-trained rate-based artificial neural network to an SNN via directly mapping the connection weights. By comparing the computational performance of SCNNs with different IP rules on the recognition of MNIST, FashionMNIST, Cifar10, and SVHN datasets, we demonstrate that the two event-based IP rules can remarkably reduce IP updating operations, contributing to sparse computations and accelerating the recognition process. This work may give insights into the modeling of brain-inspired SNNs for low-power applications.
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2021.3084955