Exploring Liquid Neural Networks on Loihi-2

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pawlak, Wiktoria Agata, Isik, Murat, Le, Dexter, Dikmen, Ismail Can
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909273898876928
author Pawlak, Wiktoria Agata
Isik, Murat
Le, Dexter
Dikmen, Ismail Can
author_facet Pawlak, Wiktoria Agata
Isik, Murat
Le, Dexter
Dikmen, Ismail Can
contents This study investigates the realm of liquid neural networks (LNNs) and their deployment on neuromorphic hardware platforms. It provides an in-depth analysis of Liquid State Machines (LSMs) and explores the adaptation of LNN architectures to neuromorphic systems, highlighting the theoretical foundations and practical applications. We introduce a pioneering approach to image classification on the CIFAR-10 dataset by implementing Liquid Neural Networks (LNNs) on state-of-the-art neuromorphic hardware platforms. Our Loihi-2 ASIC-based architecture demonstrates exceptional performance, achieving a remarkable accuracy of 91.3% while consuming only 213 microJoules per frame. These results underscore the substantial potential of LNNs for advancing neuromorphic computing and establish a new benchmark for the field in terms of both efficiency and accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20590
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Liquid Neural Networks on Loihi-2
Pawlak, Wiktoria Agata
Isik, Murat
Le, Dexter
Dikmen, Ismail Can
Emerging Technologies
Hardware Architecture
This study investigates the realm of liquid neural networks (LNNs) and their deployment on neuromorphic hardware platforms. It provides an in-depth analysis of Liquid State Machines (LSMs) and explores the adaptation of LNN architectures to neuromorphic systems, highlighting the theoretical foundations and practical applications. We introduce a pioneering approach to image classification on the CIFAR-10 dataset by implementing Liquid Neural Networks (LNNs) on state-of-the-art neuromorphic hardware platforms. Our Loihi-2 ASIC-based architecture demonstrates exceptional performance, achieving a remarkable accuracy of 91.3% while consuming only 213 microJoules per frame. These results underscore the substantial potential of LNNs for advancing neuromorphic computing and establish a new benchmark for the field in terms of both efficiency and accuracy.
title Exploring Liquid Neural Networks on Loihi-2
topic Emerging Technologies
Hardware Architecture
url https://arxiv.org/abs/2407.20590