entropy-logo

Journal Browser

Journal Browser

Information-Theoretic Approaches in Deep Learning

A special issue of Entropy (ISSN 1099-4300).

Deadline for manuscript submissions: closed (30 June 2019)

Special Issue Information

Dear Colleagues,

Deep Learning (DL) has revolutionized machine learning, especially in the last decade. In recent years, we have been observing a stunning evolution in computing technologies. As a benefit of this unprecedented development, we are capable of working with very large Neural Networks (NNs), composed of multiple layers (Deep Neural Networks), in many applications, such as object recognition-detection, speech recognition and natural language processing. DL is based on feature learning and data representation. Although many Convolutive Neural Network (CNN) and Recurrent Neural Network (RNN) based algorithms have been proposed, a comprehensive theoretical understanding of DNNs remains to be a major research area. Recently, we have seen an increase in the number of approaches that are based on information-theoretic concepts, such as Mutual Information.

In this Special Issue, we would like to collect papers focusing on both the theory and applications of information-theoretic approaches for Deep Learning. The application areas are diverse and some of them include object tracking/detection, speech recognition, natural language processing, neuroscience, bioinformatics, engineering, finance, astronomy, and Earth and space sciences.

Dr. Deniz Gencaga
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 3302 KiB  
Article
Variational Characterizations of Local Entropy and Heat Regularization in Deep Learning
by Nicolas García Trillos, Zachary Kaplan and Daniel Sanz-Alonso
Entropy 2019, 21(5), 511; https://doi.org/10.3390/e21050511 - 20 May 2019
Cited by 1 | Viewed by 3906
Abstract
The aim of this paper is to provide new theoretical and computational understanding on two loss regularizations employed in deep learning, known as local entropy and heat regularization. For both regularized losses, we introduce variational characterizations that naturally suggest a two-step scheme for [...] Read more.
The aim of this paper is to provide new theoretical and computational understanding on two loss regularizations employed in deep learning, known as local entropy and heat regularization. For both regularized losses, we introduce variational characterizations that naturally suggest a two-step scheme for their optimization, based on the iterative shift of a probability density and the calculation of a best Gaussian approximation in Kullback–Leibler divergence. Disregarding approximation error in these two steps, the variational characterizations allow us to show a simple monotonicity result for training error along optimization iterates. The two-step optimization schemes for local entropy and heat regularized loss differ only over which argument of the Kullback–Leibler divergence is used to find the best Gaussian approximation. Local entropy corresponds to minimizing over the second argument, and the solution is given by moment matching. This allows replacing traditional backpropagation calculation of gradients by sampling algorithms, opening an avenue for gradient-free, parallelizable training of neural networks. However, our presentation also acknowledges the potential increase in computational cost of naive optimization of regularized costs, thus giving a less optimistic view than existing works of the gains facilitated by loss regularization. Full article
(This article belongs to the Special Issue Information-Theoretic Approaches in Deep Learning)
Show Figures

Figure 1

Back to TopTop