Decreasing the size of the Restricted Boltzmann machine

2018/07/09 by Yohei Saito, Saito, Yohei, Takuya Kato +1
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.1807.02999

openalex publication_date 2018/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a method to decrease the number of hidden units of the restricted Boltzmann machine while avoiding decrease of the performance measured by the Kullback-Leibler divergence. Then, we demonstrate our algorithm by using numerical simulations.

Citations

• Annealed importance sampling
• Training Products of Experts by Minimizing Contrastive Divergence
• A Fast Learning Algorithm for Deep Belief Nets
• A Survey of Model Compression and Acceleration for Deep Neural Networks

Related

• An Infinite Restricted Boltzmann Machine
• Restricted Boltzmann Machines: Introduction and Review
• Pattern reconstruction with restricted Boltzmann machines
• Subspace Restricted Boltzmann Machine
• Self-regularizing restricted Boltzmann machines