• About Us
  • Contact Us
Today Headline
No Result
View All Result
  • breaking news today
    • Politics news
    • Sports
    • Science News & Society
  • Entertainment News
    • Movie
    • Gaming
  • Technology News
    • Automotive
    • Software & IT
  • Health News
    • Lifestyle
    • Insurance
  • Finance News
    • Money
  • Enterprise
  • Contact Us
  • breaking news today
    • Politics news
    • Sports
    • Science News & Society
  • Entertainment News
    • Movie
    • Gaming
  • Technology News
    • Automotive
    • Software & IT
  • Health News
    • Lifestyle
    • Insurance
  • Finance News
    • Money
  • Enterprise
  • Contact Us
No Result
View All Result
TodayHeadline
No Result
View All Result

Biologically plausible spatiotemporal adjustment helps train deep spiking neural networks

1 year ago
in Technology News
Reading Time: 3 mins read


Biologically plausible spatiotemporal adjustment helps train deep spiking neural networks

The forward and backward process of spiking neural networks. The dotted lines of different colors indicate the impact on the network at different time steps. The earlier spiking node will have more influence on the parameter update. Credit: Patterns (2022). DOI: 10.1016/j.patter.2022.100522

Spiking neural networks (SNNs) capture the most important aspects of brain information processing. They are considered a promising approach for next-generation artificial intelligence. However, the biggest problem restricting the development of SNNs is the training algorithm.

To solve this problem, a research team led by Prof. Zeng Yi from the Institute of Automation of the Chinese Academy of Sciences has proposed backpropagation (BP) with biologically plausible spatiotemporal adjustment for training deep spiking neural networks.

The associated study was published in Patterns on June 2.

Backpropagation-based training has extended SNNs to more complex network structures and tasks. However, the traditional design of BP ignores the dynamic characteristics of SNNs and is not biologically plausible.

Inspired by neural mechanisms in the brain, the researchers proposed a biologically plausible spatiotemporal adjustment to replace the traditional artificial design.

“After rethinking the relationship between membrane potential and spikes, we proposed the biologically plausible spatial adjustment of gradients to different time steps. It precisely controls the backpropagation of the error along the spatial dimension,” said Prof. Zeng Yi, corresponding author of the study.

To overcome the problem of temporal dependency of traditional spiking neurons within a single spike period, the researchers proposed a biologically plausible temporal adjustment to make the error propagate across the spikes in the temporal dimension, according to Shen Guobin, first author of the study.

The adjustment improves the performance of the SNNs and reduces energy consumption and latency. Compared with other surrogate gradient algorithms, the algorithm proposed in this study achieves 4.34% and 6.36% improvement in accuracy with only about half the energy consumption on DVS-Gesture and DVS-CIFAR10, typical datasets for temporal-sequential information processing.

“In theory, compared with artificial neural networks of the same structure, the proposed algorithm uses only about 3% of the energy to achieve competitive classification accuracy,” said Assistant Professor Zhao Dongcheng.

This study is part of the Brain-inspired Cognitive Intelligence Engine (BrainCog) project initiated by Prof. Zeng Yi’s team, an on-going scientific exploration of the infrastructure of brain-inspired artificial intelligence.


Mesoscale neural plasticity helps in AI learning


More information:
Yi Zenga, Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks, Patterns (2022). DOI: 10.1016/j.patter.2022.100522. www.cell.com/patterns/fulltext … 2666-3899(22)00119-2

Provided by
Chinese Academy of Sciences

Citation:
Biologically plausible spatiotemporal adjustment helps train deep spiking neural networks (2022, June 2)
retrieved 6 June 2022
from https://techxplore.com/news/2022-06-biologically-plausible-spatiotemporal-adjustment-deep.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.

Related Posts

Technology News

Cubs announcers slam Braves for in-game Ronald Acuña Jr. tribute

It was a big moment...

Read more

China looks to relax cross-border data security controls

Are Meta’s new Ray-Bans the first smart glasses that don’t make you look like a jerk?

Enhancing AI robustness for more secure and reliable systems

Ultrasound may rid groundwater of toxic ‘forever chemicals’

Load More
  • Trending
  • Comments
  • Latest

Robots Are Taking Over Your Surgery (and You Should Be Excited)

Whitney Webb: Bitcoin And The Plot To Destroy Financial Privacy

35 Sweet and Spooky Halloween Gifts for Teachers

Police officers ‘misusing body-worn cameras across England and Wales’

Collaboration for Conservation in Cyprus — Global Issues

Ghetto Film School to Honor Sandra Oh, Quinta Brunson, Danielle Brooks – The Hollywood Reporter

China launches yet another Yaogan spy satellite (video)

Quick Charge Podcast: September 28, 2023

Jason Lee Net Worth – How Much is Jason Worth?

Cubs announcers slam Braves for in-game Ronald Acuña Jr. tribute

About Us

Todayheadline the independent news and topics discovery
A home-grown and independent news and topic aggregation . displays breaking news linking to news websites all around the world.

Follow Us

Latest News

Ghetto Film School to Honor Sandra Oh, Quinta Brunson, Danielle Brooks – The Hollywood Reporter

China launches yet another Yaogan spy satellite (video)

Quick Charge Podcast: September 28, 2023

Ghetto Film School to Honor Sandra Oh, Quinta Brunson, Danielle Brooks – The Hollywood Reporter

China launches yet another Yaogan spy satellite (video)

Quick Charge Podcast: September 28, 2023

  • Real Estate
  • Parenting
  • Cooking
  • NFL Games On TV Today
  • Travel and Tourism
  • Home & Garden
  • Pets
  • Privacy & Policy
  • Contact
  • About

© 2023 All rights are reserved Today headline

No Result
View All Result
  • Real Estate
  • Parenting
  • Cooking
  • NFL Games On TV Today
  • Travel and Tourism
  • Home & Garden
  • Pets
  • Privacy & Policy
  • Contact
  • About

© 2023 All rights are reserved Today headline