Neuroscience inspired scientific machine learning (Part-1): Variable spiking neuron for regression

Redundant information transfer in a neural network can increase the complexity of the deep learning model, thus increasing its power consumption. We introduce in this paper a novel spiking neuron, termed Variable Spiking Neuron (VSN), which can reduce the redundant firing using lessons from biologic...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-11
Main Authors: Garg, Shailesh, Chakraborty, Souvik
Format: Article
Language:English
Subjects:
Deep learning
Energy budget
Information transfer
Machine learning
Neural networks
Neurons
Power consumption
Regression
Spiking
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Redundant information transfer in a neural network can increase the complexity of the deep learning model, thus increasing its power consumption. We introduce in this paper a novel spiking neuron, termed Variable Spiking Neuron (VSN), which can reduce the redundant firing using lessons from biological neuron inspired Leaky Integrate and Fire Spiking Neurons (LIF-SN). The proposed VSN blends LIF-SN and artificial neurons. It garners the advantage of intermittent firing from the LIF-SN and utilizes the advantage of continuous activation from the artificial neuron. This property of the proposed VSN makes it suitable for regression tasks, which is a weak point for the vanilla spiking neurons, all while keeping the energy budget low. The proposed VSN is tested against both classification and regression tasks. The results produced advocate favorably towards the efficacy of the proposed spiking neuron, particularly for regression tasks.
ISSN:2331-8422