GXNOR-Net: training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework

DOI10.1016/j.neunet.2018.01.010zbMath1434.68504arXiv1705.09283OpenAlexW2962939807WikidataQ50535241 ScholiaQ50535241MaRDI QIDQ2179802

Peng Jiao, Guoqi Li, Jing Pei, Lei Deng, Zhenzhi Wu

Publication date: 13 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1705.09283

zbMATH Keywords

discrete state transitionGXNOR-Netsparse binary networksternary neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items (2)

Active Subspace of Neural Networks: Structural Analysis and Universal Attacks ⋮ GXNOR-Net

Uses Software

• GitHub
• AxNN
• BinaryConnect
• SpiNNaker

Cites Work

• Unnamed Item
• Unnamed Item
• Memory Capacities for Synaptic and Structural Plasticity
• Efficient Associative Computation with Discrete Synapses

This page was built for publication: GXNOR-Net: training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework