Training restricted Boltzmann machines: An introduction

510 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep learning in neural networks: An overview (2014, neutral): “See the RBM/DBN tutorial (Fischer & Igel, 2014).”
Recommendation system based on deep learning methods: a systematic review and new directions (2019, methodology): “The models are trained with contrastive-divergences (CD) (Fischer and Igel 2014; Nweke et al. 2018) to provide unbiased-estimates of maximum likelihoods learning.”
A Brief Overview of Unsupervised Neural Speech Representation Learning (2022, methodology): “Other work Before the introduction of the VAE, models such as deep belief networks (DBN, Hinton, Osindero, and Teh 2006) built from stacks of restricted Boltzmann machines (Smolensky 1986; Fischer and Igel 2014) were popular.”
Training Restricted Boltzmann Machines (2015, methodology): “To improve RBM learning, Parallel Tempering (PT, Geyer, 1991) has successfully been used as a sampling method in RBM training (Salakhutdinov, 2009; Desjardins et al., 2010b; Cho et al., 2010; Fischer and Igel, 2014).”
Restricted Boltzmann machine based stock market trend prediction (2017, background): “hm), a matrix of weight W = wi,j(m × n) associated with the connection between hidden unit hj and visible unit vi as well as bias weights (offsets) ai for the visible units and bj for the hidden units [36].”