Deep Dictionary Learning vs Deep Belief Network vs Stacked Autoencoder: An Empirical Analysis

A recent work introduced the concept of deep dictionary learning. The first level is a dictionary learning stage where the inputs are the training data and the outputs are the dictionary and learned coefficients. In subsequent levels of deep dictionary learning, the learned coefficients from the previous level acts as inputs. This is an unsupervised representation learning technique. In this work we empirically compare and contrast with similar deep representation learning techniques – deep belief network and stacked autoencoder. We delve into two aspects; the first one is the robustness of the learning tool in the presence of noise and the second one is the robustness with respect to variations in the number of training samples. The experiments have been carried out on several benchmark datasets. We find that the deep dictionary learning method is the most robust.

Authors and Affiliations

1. Indraprastha Institute of Information Technology, Delhi, India

   Vanika Singhal, Anupriya Gogna & Angshul Majumdar

Corresponding author

Correspondence to Angshul Majumdar .

Editors and Affiliations

1. The University of Tokyo , Tokyo, Japan

   Akira Hirose

2. Kobe University , Kobe, Japan

   Seiichi Ozawa

3. Okinawa Institute of Science and Technology Graduate University, Onna, Japan

   Kenji Doya

4. Nara Institute of Science and Technology , Ikoma, Japan

   Kazushi Ikeda

5. Kyungpook National University , Daegu, Korea (Republic of)

   Minho Lee

6. Chinese Academy of Sciences , Beijing, China

   Derong Liu

Reprints and permissions

© 2016 Springer International Publishing AG

Policies and ethics