AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Adaptive deep spiking neural network with global-local learning via balanced excitatory and inhibitory mechanism

Tingting Jiang, Qi Xu, Xuming Ran, Jiangrong Shen, Pan Lv, Qiang Zhang, Gang Pan

ICLR 2024 · Architectures and efficiency › Spiking networks · approach: Spiking transformers

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 EIHL, a hybrid spiking neural network training algorithm that integrates local and global learning, guided by an excitation-inhibition balance mechanism.

Problem

Integrating local and global learning for training spiking neural networks, where existing integration methods do not consider which network conditions suit local versus global learning.

Approach

An excitation-inhibition mechanism assists a hybrid learning scheme so that local and global learning are each applied under network conditions where they work best, balancing their advantages.

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