Effectiveness of Unsupervised Training in Deep Learning Neural Networks

• Authors: Andrzej Rusiecki , Mirosław Kordos
• Languages of publication: PL

Abstracts

PL

Deep learning is a field of research attracting nowadays much attention, mainly because deep architectures help in obtaining outstanding results on many vision, speech and natural language processing – related tasks. To make deep learning effective, very often an unsupervised pretraining phase is applied. In this article, we present experimental study evaluating usefulness of such approach, testing on several benchmarks and different percentages of labeled data, how Contrastive Divergence (CD), one of the most popular pretraining methods, influences network generalization.

Keywords

PL

neural networks, deep learning, restricted Boltzmann Machine, contrastive divergence

• Publisher: [unknown2]
• Journal: Schedae Informaticae
• Year: 2015
• Volume: 24

Dates

published

2015

online

06 - 07 - 2016

Contributors

author

Andrzej Rusiecki

author

Mirosław Kordos