Probabilistic inference in discrete spaces can be implemented into networks of LIF neurons.
Dimitri ProbstMihai A. PetroviciIlja BytschokJohannes BillDejan PecevskiJohannes SchemmelKarlheinz MeierPublished in: Frontiers Comput. Neurosci. (2015)
Keyphrases
- probabilistic inference
- graphical models
- bayesian networks
- influence diagrams
- weighted model counting
- approximate inference
- message passing
- efficient inference
- bayesian belief networks
- conditional probabilities
- neural network
- probabilistic reasoning
- context specific independence
- belief networks
- bucket elimination
- exact inference
- random variables
- fully connected
- elimination algorithm
- search algorithm
- data sets