Low-Energy Deep Belief Networks Using Intrinsic Sigmoidal Spintronic-based Probabilistic Neurons.
Ramtin ZandKerem Yunus CamsariSteven D. PyleIbrahim AhmedChris H. KimRonald F. DeMaraPublished in: ACM Great Lakes Symposium on VLSI (2018)
Keyphrases
- low energy
- deep belief networks
- generative model
- probabilistic model
- electron microscopy
- neural network
- restricted boltzmann machine
- deep learning
- unsupervised learning
- protein folding
- bayesian networks
- coarse grained
- machine learning
- conditional probabilities
- hierarchical models
- hidden layer
- belief networks
- action recognition
- markov random field
- pairwise
- learning algorithm