LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Apolinario, Marco Paul E., Roy, Arani, Roy, Kaushik
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915370881777664
author Apolinario, Marco Paul E.
Roy, Arani
Roy, Kaushik
author_facet Apolinario, Marco Paul E.
Roy, Arani
Roy, Kaushik
contents Training deep neural networks (DNNs) using traditional backpropagation (BP) presents challenges in terms of computational complexity and energy consumption, particularly for on-device learning where computational resources are limited. Various alternatives to BP, including random feedback alignment, forward-forward, and local classifiers, have been explored to address these challenges. These methods have their advantages, but they can encounter difficulties when dealing with intricate visual tasks or demand considerable computational resources. In this paper, we propose a novel Local Learning rule inspired by neural activity Synchronization phenomena (LLS) observed in the brain. LLS utilizes fixed periodic basis vectors to synchronize neuron activity within each layer, enabling efficient training without the need for additional trainable parameters. We demonstrate the effectiveness of LLS and its variations, LLS-M and LLS-MxM, on multiple image classification datasets, achieving accuracy comparable to BP with reduced computational complexity and minimal additional parameters. Specifically, LLS achieves comparable performance with up to $300 \times$ fewer multiply-accumulate (MAC) operations and half the memory requirements of BP. Furthermore, the performance of LLS on the Visual Wake Word (VWW) dataset highlights its suitability for on-device learning tasks, making it a promising candidate for edge hardware implementations.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15868
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization
Apolinario, Marco Paul E.
Roy, Arani
Roy, Kaushik
Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
Training deep neural networks (DNNs) using traditional backpropagation (BP) presents challenges in terms of computational complexity and energy consumption, particularly for on-device learning where computational resources are limited. Various alternatives to BP, including random feedback alignment, forward-forward, and local classifiers, have been explored to address these challenges. These methods have their advantages, but they can encounter difficulties when dealing with intricate visual tasks or demand considerable computational resources. In this paper, we propose a novel Local Learning rule inspired by neural activity Synchronization phenomena (LLS) observed in the brain. LLS utilizes fixed periodic basis vectors to synchronize neuron activity within each layer, enabling efficient training without the need for additional trainable parameters. We demonstrate the effectiveness of LLS and its variations, LLS-M and LLS-MxM, on multiple image classification datasets, achieving accuracy comparable to BP with reduced computational complexity and minimal additional parameters. Specifically, LLS achieves comparable performance with up to $300 \times$ fewer multiply-accumulate (MAC) operations and half the memory requirements of BP. Furthermore, the performance of LLS on the Visual Wake Word (VWW) dataset highlights its suitability for on-device learning tasks, making it a promising candidate for edge hardware implementations.
title LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization
topic Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.15868