Analysis of time-frequency scattering transforms

DOI10.1016/j.acha.2017.08.005zbMath1419.42025arXiv1606.08677OpenAlexW2589910641MaRDI QIDQ2424627

Wojciech Czaja, Weilin Li

Publication date: 25 June 2019

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1606.08677

zbMATH Keywords

Gabor framesscattering transformtime-frequencyconvolutional neural networksfeature extractor

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) General harmonic expansions, frames (42C15) Miscellaneous applications of operator theory (47N99)

Related Items (8)

Asymptotic analysis of higher-order scattering transform of Gaussian processes ⋮ Central and Noncentral Limit Theorems Arising from the Scattering Transform and Its Neural Activation Generalization ⋮ Geometric scattering on measure spaces ⋮ Stability of the scattering transform for deformations with minimal regularity ⋮ On generalizations of the nonwindowed scattering transform ⋮ Rotationally invariant time-frequency scattering transforms ⋮ Gabor neural networks with proven approximation properties ⋮ Stability for the training of deep neural networks and other classifiers

Uses Software

• darch
• ImageNet
• ScatNet
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• \(\alpha\)-Molecules
• Note on best possible bounds for determinants of matrices close to the identity matrix
• Gabor frames and directional time-frequency analysis
• Harmonic analysis of neural networks
• Provable approximation properties for deep neural networks
• Discrete directional Gabor frames
• Piecewise polynomial, positive definite and compactly supported radial functions of minimal degree
• Rotationally invariant time-frequency scattering transforms
• Wavelets with composite dilations and their MRA properties
• Group Invariant Scattering
• Integration and Modern Analysis
• Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression
• The wavelet transform, time-frequency localization and signal analysis
• Ten Lectures on Wavelets
• New tight frames of curvelets and optimal representations of objects with piecewise C² singularities
• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• Energy Propagation in Deep Convolutional Neural Networks
• Anisotropic shearlet transforms for L²
• Optimally Sparse Multidimensional Representation Using Shearlets
• A Fast Learning Algorithm for Deep Belief Nets

This page was built for publication: Analysis of time-frequency scattering transforms