Decreasing the size of the Restricted Boltzmann machine
Yohei Saito, Takuya Kato
TL;DR
This paper introduces a method to reduce the number of hidden units in a restricted Boltzmann machine without compromising its performance, validated through numerical simulations.
Contribution
The paper presents a novel algorithm for decreasing hidden units in RBMs while maintaining their performance, which is demonstrated via simulations.
Findings
Effective reduction of hidden units achieved
Performance preserved as measured by KL divergence
Algorithm validated through numerical experiments
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Model Reduction and Neural Networks · Neural Networks and Applications