Header

UZH-Logo

Maintenance Infos

The Importance of Space and Time for Signal Processing in Neuromorphic Agents: The Challenge of Developing Low-Power, Autonomous Agents That Interact With the Environment


Indiveri, Giacomo; Sandamirskaya, Yulia (2019). The Importance of Space and Time for Signal Processing in Neuromorphic Agents: The Challenge of Developing Low-Power, Autonomous Agents That Interact With the Environment. Institute of Electrical and Electronics Engineers Signal Processing Magazine, 36(6):16-28.

Abstract

Artificial neural networks (ANNs) and computational neuroscience models have made tremendous progress, enabling us to achieve impressive results in artificial intelligence applications, such as image recognition, natural language processing, and autonomous driving. Despite this, biological neural systems consume orders of magnitude less energy than today's ANNs and are much more flexible and robust. This adaptivity and efficiency gap is partially explained by the computing substrate of biological neural processing systems that is fundamentally different from the way today?s computers are built. Biological systems use in-memory computing elements operating in a massively parallel way rather than time-multiplexed computing units that are reused in a sequential fashion. Moreover, the activity of biological neurons follows continuous-time dynamics in real, physical time instead of operating on discrete temporal cycles abstracted away from real time.

Abstract

Artificial neural networks (ANNs) and computational neuroscience models have made tremendous progress, enabling us to achieve impressive results in artificial intelligence applications, such as image recognition, natural language processing, and autonomous driving. Despite this, biological neural systems consume orders of magnitude less energy than today's ANNs and are much more flexible and robust. This adaptivity and efficiency gap is partially explained by the computing substrate of biological neural processing systems that is fundamentally different from the way today?s computers are built. Biological systems use in-memory computing elements operating in a massively parallel way rather than time-multiplexed computing units that are reused in a sequential fashion. Moreover, the activity of biological neurons follows continuous-time dynamics in real, physical time instead of operating on discrete temporal cycles abstracted away from real time.

Statistics

Citations

Dimensions.ai Metrics
7 citations in Web of Science®
9 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

12 downloads since deposited on 14 Feb 2020
12 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Physical Sciences > Signal Processing
Physical Sciences > Electrical and Electronic Engineering
Physical Sciences > Applied Mathematics
Uncontrolled Keywords:Signal Processing, Electrical and Electronic Engineering, Applied Mathematics
Language:English
Date:1 November 2019
Deposited On:14 Feb 2020 10:04
Last Modified:29 Jul 2020 14:15
Publisher:Institute of Electrical and Electronics Engineers
ISSN:1053-5888
Additional Information:© 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.
OA Status:Green
Publisher DOI:https://doi.org/10.1109/msp.2019.2928376
Project Information:
  • : FunderH2020
  • : Grant ID724295
  • : Project TitleNeuroAgents - Neuromorphic Electronic Agents: from sensory processing to autonomous cognitive behavior

Download

Green Open Access