Learning quantized neural nets by coarse gradient method for nonlinear classification

DOI10.1007/s40687-021-00281-4zbMath1476.90263arXiv2011.11256OpenAlexW3189554725MaRDI QIDQ2050846

Ziang Long, Penghang Yin, Jack X. Xin

Publication date: 1 September 2021

Published in: Research in the Mathematical Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.11256

zbMATH Keywords

discrete optimizationnonlinear classificationcoarse gradient descentquantized neural networks

Mathematics Subject Classification ID

Analysis of algorithms (68W40) Nonconvex programming, global optimization (90C26)

Related Items (1)

Unnamed Item

Uses Software

• ImageNet
• BinaryConnect
• BinaryNet
• DoReFa-Net
• AlexNet
• CosFace
• Faster R-CNN

Cites Work

• Linear feature transform and enhancement of classification on deep neural network
• Large margin classification using the perceptron algorithm
• Blended coarse gradient descent for full quantization of deep neural networks
• Relu Deep Neural Networks and Linear Finite Elements
• BinaryRelax: A Relaxation Approach for Training Deep Neural Networks with Quantized Weights
• Unnamed Item
• Unnamed Item

This page was built for publication: Learning quantized neural nets by coarse gradient method for nonlinear classification