Fine Tuning Deep Boltzmann Machines Through Meta-Heuristic Approaches

Author(s)

Passos, Leandro A. ; Rodrigues, Douglas R. ; Papa, Joao P. ; IEEE

• Document type: Journal article
• Source: 2018 IEEE 12TH INTERNATIONAL SYMPOSIUM ON APPLIED COMPUTATIONAL INTELLIGENCE AND INFORMATICS (SACI); v. N/A, p. 6-pg., 2018-01-01.

Abstract

The Deep learning framework has been widely used in different applications from medicine to engineering. However, there is a lack of works that manage to deal with the issue of hyperparameter fine-tuning, since machine learning techniques often require a considerable human effort in this task. In this paper, we propose to fine-tune Deep Boltzmann Machines using meta-heuristic techniques, which do not require the computation of the gradient of the fitness function, that may be insurmountable in high-dimensional optimization spaces. We demonstrate the validity of the proposed approach against Deep Belief Networks concerning binary image reconstruction. (AU)

• FAPESP's process: 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?
• Grantee: Alexandre Xavier Falcão
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 16/19403-6 - Energy-based learning models and their applications
• Grantee: João Paulo Papa
• Support Opportunities: Regular Research Grants
• FAPESP's process: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry
• Grantee: Francisco Louzada Neto
• Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC