Scholarlink

Modern Deep Neural Networks, have an ever increasing number of parameters that need to be optimised on enormous amounts of data during training. Even with advanced hardware, the training process for these models can take months and can consume large amounts of energy. This prolonged use of computing resources drives up cost significantly. In this paper we explore how one uses Spiking Neural Network (SNN) in LSTM via the NeuroAI toolkit. Compared against the traditional LSTM, the training time of our adapted LSTM significantly decreased by as much as 75% but with an increase in accuracy. We also demonstrate that using the SNN decreases the amount of CPU used by as much as 14% during training, thereby being more efficient and sustainable.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Accelerating LSTM Model Training Through Biologically Inspired NeuroAI and Investigating Novel Applications

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Robert Tracey,
  • M. Emre Sahin,
  • Carol Mak

摘要

Modern Deep Neural Networks, have an ever increasing number of parameters that need to be optimised on enormous amounts of data during training. Even with advanced hardware, the training process for these models can take months and can consume large amounts of energy. This prolonged use of computing resources drives up cost significantly. In this paper we explore how one uses Spiking Neural Network (SNN) in LSTM via the NeuroAI toolkit. Compared against the traditional LSTM, the training time of our adapted LSTM significantly decreased by as much as 75% but with an increase in accuracy. We also demonstrate that using the SNN decreases the amount of CPU used by as much as 14% during training, thereby being more efficient and sustainable.