A topological insight into restricted Boltzmann machines (extented abstract)

Decebal Constantin Mocanu, Elena Mocanu, Phuong H. Nguyen, Madeleine Gibescu, Antonio Liotta

Research output: Contribution to conferenceAbstractAcademic

3 Downloads (Pure)

Abstract

Restricted Boltzmann Machines (RBMs) and models derived from them have been successfully used as basic building blocks in deep neural networks for automatic features extraction, unsupervised weights initialization, but also as standalone models for density estimation, activity recognition and so on. Thus, their generative and discriminative capabilities, but also their computational time are instrumental to a wide range of applications. The main contribution of his paper is to study the above problems by looking at RBMs and Gaussian RBMs (GRBMs) from a topological perspective, bringing insights from network science, an extension of graph theory which analyzes real world complex networks.
Original languageEnglish
Number of pages2
Publication statusPublished - 11 Nov 2016
Externally publishedYes
Event28th Benelux Conference on Artificial Intelligence, BNAIC 2016 - Hotel Casa, Amsterdam, Netherlands
Duration: 10 Nov 201611 Nov 2016
Conference number: 28

Conference

Conference28th Benelux Conference on Artificial Intelligence, BNAIC 2016
Abbreviated titleBNAIC
CountryNetherlands
CityAmsterdam
Period10/11/1611/11/16

Fingerprint Dive into the research topics of 'A topological insight into restricted Boltzmann machines (extented abstract)'. Together they form a unique fingerprint.

Cite this