A Deep Incremental Boltzmann Machine for Modeling Context in Robots

Context is an essential capability for robots that are to be as adaptive as possible in challenging environments. Although there are many context modeling efforts, they assume a fixed structure and number of contexts. In this paper, we propose an incremental deep model that extends Restricted Boltzm...

Full description

Saved in:
Bibliographic Details
Main Authors Doğan, Fethiye Irmak, Çelikkanat, Hande, Kalkan, Sinan
Format Journal Article
LanguageEnglish
Published 13.10.2017
Subjects
Computer Science - Learning
Computer Science - Robotics
Online AccessGet full text

Cover

More Information
Summary:Context is an essential capability for robots that are to be as adaptive as possible in challenging environments. Although there are many context modeling efforts, they assume a fixed structure and number of contexts. In this paper, we propose an incremental deep model that extends Restricted Boltzmann Machines. Our model gets one scene at a time, and gradually extends the contextual model when necessary, either by adding a new context or a new context layer to form a hierarchy. We show on a scene classification benchmark that our method converges to a good estimate of the contexts of the scenes, and performs better or on-par on several tasks compared to other incremental models or non-incremental models.
DOI:10.48550/arxiv.1710.04975