Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
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...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Journal of Low Power Electronics and Applications |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9268/15/1/4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850090638123466752 |
|---|---|
| author | Oscar I. Alvarez-Canchila Andres Espinal Alberto Patiño-Saucedo Horacio Rostro-Gonzalez |
| author_facet | Oscar I. Alvarez-Canchila Andres Espinal Alberto Patiño-Saucedo Horacio Rostro-Gonzalez |
| author_sort | Oscar I. Alvarez-Canchila |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-6c0eeb0d23a247de85f55e6437648a3f |
| institution | DOAJ |
| issn | 2079-9268 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Low Power Electronics and Applications |
| spelling | doaj-art-6c0eeb0d23a247de85f55e6437648a3f2025-08-20T02:42:31ZengMDPI AGJournal of Low Power Electronics and Applications2079-92682025-01-01151410.3390/jlpea15010004Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic HardwareOscar I. Alvarez-Canchila0Andres Espinal1Alberto Patiño-Saucedo2Horacio Rostro-Gonzalez3Department of Electronics Engineering, DICIS—University of Guanajuato, Carretera Salamanca—Valle de Santiago km 3.5 + 1.8 kms, Salamanca 36885, MexicoDepartment of Organizational Studies, University of Guanajuato, Fraccionamiento 1, Col. El Establo S/N, Guanajuato 36250, MexicoIMSE-CNM—Seville Institute of Microelectronics, 41092 Sevilla, SpainDepartment of Electronics Engineering, DICIS—University of Guanajuato, Carretera Salamanca—Valle de Santiago km 3.5 + 1.8 kms, Salamanca 36885, MexicoIn 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.https://www.mdpi.com/2079-9268/15/1/4Liquid State Machinereservoir computingneuromorphic computingParticle Swarm OptimizationSpiNNaker |
| spellingShingle | Oscar I. Alvarez-Canchila Andres Espinal Alberto Patiño-Saucedo Horacio Rostro-Gonzalez Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware Journal of Low Power Electronics and Applications Liquid State Machine reservoir computing neuromorphic computing Particle Swarm Optimization SpiNNaker |
| title | Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware |
| title_full | Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware |
| title_fullStr | Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware |
| title_full_unstemmed | Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware |
| title_short | Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware |
| title_sort | optimizing reservoir separability in liquid state machines for spatio temporal classification in neuromorphic hardware |
| topic | Liquid State Machine reservoir computing neuromorphic computing Particle Swarm Optimization SpiNNaker |
| url | https://www.mdpi.com/2079-9268/15/1/4 |
| work_keys_str_mv | AT oscarialvarezcanchila optimizingreservoirseparabilityinliquidstatemachinesforspatiotemporalclassificationinneuromorphichardware AT andresespinal optimizingreservoirseparabilityinliquidstatemachinesforspatiotemporalclassificationinneuromorphichardware AT albertopatinosaucedo optimizingreservoirseparabilityinliquidstatemachinesforspatiotemporalclassificationinneuromorphichardware AT horaciorostrogonzalez optimizingreservoirseparabilityinliquidstatemachinesforspatiotemporalclassificationinneuromorphichardware |