Memory-error tolerance of scalable and highly parallel architecture for restricted Boltzmann machines in Deep Belief Network.
Kodai UeyoshiTakao MarukameTetsuya AsaiMasato MotomuraAlexandre SchmidPublished in: ISCAS (2016)
Keyphrases
- deep belief networks
- restricted boltzmann machine
- deep learning
- unsupervised learning
- hierarchical models
- probabilistic model
- generative model
- probabilistic graphical models
- semi supervised
- conditional random fields
- learning algorithm
- approximate inference
- machine learning
- neural network
- sparse coding
- supervised learning
- graphical models
- hierarchical model
- pairwise
- bayesian networks
- dynamic programming
- hidden markov models