AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework

Xinyu Shi, Jianhao Ding, Zecheng Hao, Zhaofei Yu

ICLR 2024 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an unstructured pruning framework for spiking neural networks to improve energy efficiency by exploiting sparsity beyond existing energy-reduction methods.

Problem

Deep spiking neural networks have lost much of their energy-efficiency advantage, and existing energy-reduction methods do not fully exploit sparsity, while powerful pruning techniques are not tailored to SNNs.

Approach

An unstructured pruning framework designed for SNNs that targets sparsity to reduce energy consumption on neuromorphic hardware, rather than relying on existing energy-reduction methods or generic pruning.

Experimental setup

Metrics: energy consumption

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy