University of Hertfordshire

By the same authors

Sparse feature extraction model with Independent Subspace Analysis

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

View graph of relations
Original languageEnglish
Title of host publicationMachine Learning, Optimization, and Data Science
EditorsG Nicosia , P Pardalos, G Giuffrida, R Umeton, V Sciacca
PublisherSpringer
Chapter42
Pages494-505
Number of pages12
ISBN (Electronic)978-3-030-13709-0
ISBN (Print)978-3-030-13708-3
DOIs
Publication statusPublished - 14 Feb 2019
Event4th International Conference: LOD 2018 - Volterra, Italy
Duration: 13 Sep 201816 Sep 2018

Publication series

Name Lecture Notes in Computer Science
PublisherSpringer
Volume11331

Conference

Conference4th International Conference
CountryItaly
CityVolterra
Period13/09/1816/09/18

Abstract

Recent advances in deep learning models have demonstrated remarkable accuracy in object classification. However, the limitations of Convolutional Neural Networks such as the requirement for a large collection of labeled data for training and supervised learning process has called for enhanced feature representation and for unsupervised models.

In this paper we propose a novel unsupervised sparsity-based model using Independent Subspace Analysis (ISA) to implement a hierarchical network for feature extraction. The results of our empirical evaluation demonstrates an improved classification accuracy when max pooling is paired with square pooling within each layer. In addition to accuracy, we further show that it also reduces the data dimensions within the layers outperforming known sparsity-based models.

Notes

© Springer Nature Switzerland AG 2019

ID: 16251066