Repository logo
 

Multi-Resolution Dual-Tree Wavelet Scattering Network for Signal Classification

Published version
Peer-reviewed

Type

Conference Object

Change log

Authors

Singh, A 
Kingsbury, N 

Abstract

This paper introduces a Deep Scattering network that utilizes Dual-Tree complex wavelets to extract multi-scale translation invariant representations from an input signal. The computationally efficient Dual-Tree wavelets decompose the input signal into equally spaced representations over scales. Translation invariance is introduced in the representations by applying a non-linearity over a region followed by averaging. The discriminatory information from the equally spaced locally smooth signal representations aids the learning of the classi- fier. The proposed network is shown to outperform Mallat’s ScatterNet [1] on four datasets with different modalities, both for classification accuracy and computational efficiency.

Description

Keywords

DTCWT, scattering network, convolutional neural network, USPS dataset, UCI datasets

Journal Title

11th International Conference on Mathematics in Signal Processing, 12–14 December 2016, Austin Court, Birmingham, UK

Conference Name

11th International Conference on Mathematics in Signal Processing

Journal ISSN

Volume Title

Publisher

Institute of Mathematics and its Applications
Sponsorship
Cambridge Trust