Asynchronous Neuromorphic Optimization with Lava

TL;DR

This paper introduces a novel asynchronous Bayesian optimization framework compatible with Intel's Lava platform and Loihi 2 hardware, demonstrating its application to satellite scheduling on neuromorphic systems.

Contribution

The paper presents a new asynchronous optimization framework integrated with Lava, enabling efficient Bayesian optimization on neuromorphic hardware like Loihi 2.

Findings

Successful implementation of asynchronous optimization on Loihi 2 hardware

Application to satellite scheduling problem demonstrating practical utility

Framework compatible with event-based neuromorphic systems

Abstract

Performing optimization with event-based asynchronous neuromorphic systems presents significant challenges. Intel's neuromorphic computing framework, Lava, offers an abstract application programming interface designed for constructing event-based computational graphs. In this study, we introduce a novel framework tailored for asynchronous Bayesian optimization that is also compatible with Loihi 2. We showcase the capability of our asynchronous optimization framework by connecting it with a graph-based satellite scheduling problem running on physical Loihi 2 hardware.