Exploring Liquid Neural Networks on Loihi-2

TL;DR

This paper explores the implementation of liquid neural networks on neuromorphic hardware, demonstrating high accuracy and efficiency in image classification tasks, and establishing new benchmarks for neuromorphic computing.

Contribution

It introduces a novel approach to deploying liquid neural networks on Loihi-2 hardware, achieving state-of-the-art performance and energy efficiency in image classification.

Findings

Achieved 91.3% accuracy on CIFAR-10

Consumed only 213 microJoules per frame

Established new benchmarks in neuromorphic efficiency and accuracy

Abstract

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.