33.1 A 74 TMACS/W CMOS-RRAM Neurosynaptic Core with Dynamically Reconfigurable Dataflow and In-situ Transposable Weights for Probabilistic Graphical Models.
Weier WanRajkumar KubendranSukru Burc EryilmazWenqiang ZhangYan LiaoDabin WuStephen R. DeissBin GaoPriyanka RainaSiddharth JoshiHuaqiang WuGert CauwenberghsH.-S. Philip WongPublished in: ISSCC (2020)
Keyphrases
- probabilistic graphical models
- graphical models
- markov networks
- first order logic
- approximate inference
- belief propagation
- latent variables
- probabilistic inference
- parameter learning
- exact inference
- conditional random fields
- random variables
- bayesian networks
- fuzzy measures
- neural network
- special case
- hidden variables
- belief functions
- image segmentation
- structure learning
- data mining