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.
@article{arxiv.2407.20590,
title = {Exploring Liquid Neural Networks on Loihi-2},
author = {Wiktoria Agata Pawlak and Murat Isik and Dexter Le and Ismail Can Dikmen},
journal= {arXiv preprint arXiv:2407.20590},
year = {2024}
}