Neuromorphic on-chip reservoir computing with spiking neural network architectures

TL;DR

This paper explores neuromorphic reservoir computing using spiking neural networks with integrate-and-fire neurons, optimizing network architectures for specific tasks like chaotic dynamics and time series forecasting, and evaluating energy efficiency on Loihi hardware.

Contribution

It introduces a meta-learning approach with simulated annealing to optimize reservoir network structures for different tasks in neuromorphic hardware.

Findings

Task-specific network architectures improve performance.

Meta-learning effectively identifies optimal configurations.

Loihi implementation demonstrates energy efficiency.

Abstract

Reservoir computing is a promising approach for harnessing the computational power of recurrent neural networks while dramatically simplifying training. This paper investigates the application of integrate-and-fire neurons within reservoir computing frameworks for two distinct tasks: capturing chaotic dynamics of the H\'enon map and forecasting the Mackey-Glass time series. Integrate-and-fire neurons can be implemented in low-power neuromorphic architectures such as Intel Loihi. We explore the impact of network topologies created through random interactions on the reservoir's performance. Our study reveals task-specific variations in network effectiveness, highlighting the importance of tailored architectures for distinct computational tasks. To identify optimal network configurations, we employ a meta-learning approach combined with simulated annealing. This method efficiently explores the space of possible network structures, identifying architectures that excel in different scenarios. The resulting networks demonstrate a range of behaviors, showcasing how inherent architectural features influence task-specific capabilities. We study the reservoir computing performance using a custom integrate-and-fire code, Intel's Lava neuromorphic computing software framework, and via an on-chip implementation in Loihi. We conclude with an analysis of the energy performance of the Loihi architecture.