Decreasing the size of the Restricted Boltzmann machine
arXiv:1807.02999v23 citations
Originality Synthesis-oriented
AI Analysis
This work addresses efficiency in machine learning models for practitioners, but it appears incremental as it focuses on optimizing an existing method.
The authors tackled the problem of reducing the size of Restricted Boltzmann Machines (RBMs) without compromising performance, measured by Kullback-Leibler divergence, and demonstrated their algorithm through numerical simulations.
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.