Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
Author
Other authors
Publication date
2025-03ISSN
2079-9268
Abstract
In this paper, we propose an optimization approach using Particle Swarm Optimization (PSO) to enhance reservoir separability in Liquid State Machines (LSMs) for spatio-temporal classification in neuromorphic systems. By leveraging PSO, our method fine-tunes reservoir parameters, neuron dynamics, and connectivity patterns, maximizing separability while aligning with the resource constraints typical of neuromorphic hardware. This approach was validated in both software (NEST) and on neuromorphic hardware (SpiNNaker), demonstrating notable results in terms of accuracy and low energy consumption when using SpiNNaker. Specifically, our approach addresses two problems: Frequency Recognition (FR) with five classes and Pattern Recognition (PR) with four, eight, and twelve classes. For instance, in the Mono-objective approach running in NEST, accuracies ranged from 81.09% to 95.52% across the benchmarks under study. The Multi-objective approach outperformed the Mono-objective approach, delivering accuracies ranging from 90.23% to 98.77%, demonstrating its superior scalability for LSM implementations. On the SpiNNaker platform, the mono-objective approach achieved accuracies ranging from 86.20% to 97.70% across the same benchmarks, with the Multi-objective approach further improving accuracies, ranging from 94.42% to 99.52%. These results show that, in addition to slight accuracy improvements, hardware-based implementations offer superior energy efficiency with a lower execution time. For example, SpiNNaker operates at around 1–5 watts per chip, while traditional systems can require 50–100 watts for similar tasks, highlighting the significant energy savings of neuromorphic hardware. These results underscore the scalability and effectiveness of PSO-optimized LSMs on resource-limited neuromorphic platforms, showcasing both improved classification performance and the advantages of energy-efficient processing.
Document Type
Article
Document version
Published version
Language
English
Subject (CDU)
004 - Computer science and technology. Computing. Data processing
616.8 - Neurology. Neuropathology. Nervous system
Keywords
Liquid State Machine
Reservoir computing
Neuromorphic computing
Particle Swarm Optimization
SpiNNaker
Màquina d'estat líquid
Computació de reservori
Enginyeria neuromòrfica
Pages
p.21
Publisher
MDPI
Is part of
Journal of Low Power Electronics and Applications 2025, 15(1), 4
This item appears in the following Collection(s)
Rights
© L'autor/a
Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by/4.0/