BlocTrain: Block-Wise Conditional Training and Inference for Efficient Spike-Based Deep Learning.

ABSTRACT: Spiking neural networks (SNNs), with their inherent capability to learn sparse spike-based input representations over time, offer a promising solution for enabling the next generation of intelligent autonomous systems. Nevertheless, end-to-end training of deep SNNs is both compute- and memory-intensive because of the need to backpropagate error gradients through time. We propose BlocTrain, which is a scalable and complexity-aware incremental algorithm for memory-efficient training of deep SNNs. We divide a deep SNN into blocks, where each block consists of few convolutional layers followed by a classifier. We train the blocks sequentially using local errors from the classifier. Once a given block is trained, our algorithm dynamically figures out easy vs. hard classes using the class-wise a

SUBMITTER: Srinivasan G 

PROVIDER: S-EPMC8586528 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature