Liquid State Machine on SpiNNaker for Spatio-Temporal Classification Tasks

Alberto Patiño-Saucedo, Horacio Rostro-González, Teresa Serrano-Gotarredona, Bernabé Linares-Barranco

Producció científica: Article en revista indexadaArticleAvaluat per experts

10 Cites (Scopus)

Resum

Liquid State Machines (LSMs) are computing reservoirs composed of recurrently connected Spiking Neural Networks which have attracted research interest for their modeling capacity of biological structures and as promising pattern recognition tools suitable for their implementation in neuromorphic processors, benefited from the modest use of computing resources in their training process. However, it has been difficult to optimize LSMs for solving complex tasks such as event-based computer vision and few implementations in large-scale neuromorphic processors have been attempted. In this work, we show that offline-trained LSMs implemented in the SpiNNaker neuromorphic processor are able to classify visual events, achieving state-of-the-art performance in the event-based N-MNIST dataset. The training of the readout layer is performed using a recent adaptation of back-propagation-through-time (BPTT) for SNNs, while the internal weights of the reservoir are kept static. Results show that mapping our LSM from a Deep Learning framework to SpiNNaker does not affect the performance of the classification task. Additionally, we show that weight quantization, which substantially reduces the memory footprint of the LSM, has a small impact on its performance.

Idioma originalAnglès
Número d’article819063
RevistaFrontiers in Neuroscience
Volum16
DOIs
Estat de la publicacióPublicada - 14 de març 2022
Publicat externament

Fingerprint

Navegar pels temes de recerca de 'Liquid State Machine on SpiNNaker for Spatio-Temporal Classification Tasks'. Junts formen un fingerprint únic.

Com citar-ho