Pattern Training, Inference, and Regeneration Demonstration Using On-Chip Trainable Neuromorphic Chips for Spiking Restricted Boltzmann Machine.
Uicheol ShinMasatoshi IshiiAtsuya OkazakiMegumi ItoMalte J. RaschWanki KimAkiyo NomuraWonseok ChoiDooyong KohKohji HosokawaMatthew BrightSkySeiji MunetohSangBum KimPublished in: Adv. Intell. Syst. (2022)
Keyphrases
- restricted boltzmann machine
- high speed
- deep learning
- loopy belief propagation
- conditional random fields
- probabilistic graphical models
- feed forward
- belief propagation
- structured prediction
- object recognition
- learning algorithm
- hidden layer
- training set
- semi supervised
- neural network
- probabilistic inference
- stereo matching
- bio inspired
- parameter estimation
- supervised learning
- machine learning