A Generalized Spiking Locally Competitive Algorithm for Multiple Optimization Problems

TL;DR

This paper presents a generalized spiking LCA that is biologically plausible, adaptable to various neuron models, converges reliably, outperforms traditional methods in speed, and is compatible with neuromorphic hardware for diverse optimization tasks.

Contribution

The paper introduces a flexible, biologically plausible spiking LCA that converges reliably and is compatible with neuromorphic chips, enabling faster and more adaptable optimization solutions.

Findings

Faster early convergence compared to FISTA in practical tasks

Compatible with neuromorphic hardware like Loihi

Demonstrates superior performance in signal recovery

Abstract

We introduce a generalized Spiking Locally Competitive Algorithm (LCA) that is biologically plausible and exhibits adaptability to a large variety of neuron models and network connectivity structures. In addition, we provide theoretical evidence demonstrating the algorithm's convergence in optimization problems of signal recovery. Furthermore, our algorithm demonstrates superior performance over traditional optimization methods, such as FISTA, particularly by achieving faster early convergence in practical scenarios including signal denoising, seismic wave detection, and computed tomography reconstruction. Notably, our algorithm is compatible with neuromorphic chips, such as Loihi, facilitating efficient multitasking within the same chip architecture - a capability not present in existing algorithms. These advancements make our generalized Spiking LCA a promising solution for real-world applications, offering significant improvements in execution speed and flexibility for neuromorphic computing systems.