8 citations · 13 across the 4 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2014
Approximated Infomax Early Stopping: Revisiting Gaussian RBMs on Natural Images
Taichi Kiwaki, Takaki Makino, Kazuyuki Aihara
We pursue an early stopping technique that helps Gaussian Restricted Boltzmann Machines (GRBMs) to gain good natural image representations in terms of overcompleteness and data fit…
stat.ML2011★ 1 cited
Restricted Collapsed Draw: Accurate Sampling for Hierarchical Chinese Restaurant Process Hidden Markov Models
Takaki Makino, Shunsuke Takei, Issei Sato +1
We propose a restricted collapsed draw (RCD) sampler, a general Markov chain Monte Carlo sampler of simultaneous draws from a hierarchical Chinese restaurant process (HCRP) with re…