A Mathematical Motivation for Complex-Valued Convolutional Networks

DOI10.1162/NECO_a_00824zbMath1472.68161arXiv1503.03438WikidataQ39987686 ScholiaQ39987686MaRDI QIDQ5380421

Mark Tygert, Joan Bruna, Arthur D. Szlam, Soumith Chintala, Yann LeCun, Serkan Piantino

Publication date: 4 June 2019

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

Full work available at URL: https://arxiv.org/abs/1503.03438

Mathematics Subject Classification ID

Multivariate analysis (62H99) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (5)

Scale-invariant learning and convolutional networks ⋮ Towards understanding theoretical advantages of complex-reaction networks ⋮ A neural network warm-start approach for the inverse acoustic obstacle scattering problem ⋮ The universal approximation theorem for complex-valued neural networks ⋮ Lipschitz properties for deep convolutional networks

Uses Software

• Steerable pyramid
• SIFT
• CIFAR
• ImageNet
• SURF
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Scale-invariant learning and convolutional networks
• On advances in statistical modeling of natural images
• Local discriminant bases and their applications
• Intermittent process analysis with scattering moments
• Ten Lectures on Wavelets
• Locally stationary covariance and signal estimation with macrotiles
• Introduction to Digital Speech Processing

This page was built for publication: A Mathematical Motivation for Complex-Valued Convolutional Networks