Publication:
Implementing the analogous neural network using chaotic strange attractors

Thumbnail Image

School / College / Institute

Program

KU-Authors

KU Authors

Co-Authors

Publication Date

Language

Embargo Status

Journal Title

Journal ISSN

Volume Title

Alternative Title

Abstract

Machine learning studies need colossal power to process massive datasets and train neural networks to reach high accuracies, which have become gradually unsustainable. Limited by the von Neumann bottleneck, current computing architectures and methods fuel this high power consumption. Here, we present an analog computing method that harnesses chaotic nonlinear attractors to perform machine learning tasks with low power consumption. Inspired by neuromorphic computing, our model is a programmable, versatile, and generalized platform for machine learning tasks. Our mode provides exceptional performance in clustering by utilizing chaotic attractors’ nonlinear mapping and sensitivity to initial conditions. When deployed as a simple analog device, it only requires milliwatt-scale power levels while being on par with current machine learning techniques. We demonstrate low errors and high accuracies with our model for regression and classification-based learning tasks.

Source

Publisher

Springer Nature

Subject

Electrical and electronics engineering

Citation

Has Part

Source

Communications Engineering

Book Series Title

Edition

DOI

10.1038/s44172-024-00242-z

item.page.datauri

Link

Rights

Copyrights Note

Endorsement

Review

Supplemented By

Referenced By

4

Views

4

Downloads

View PlumX Details