Online Learning with Hidden Markov Models

133 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Synaptic weight decay with selective consolidation enables fast learning without catastrophic forgetting (2019, background): “The fast synaptic plasticity may enable the retention of information in working memory (Mongillo and Denève, 2008) that must fade out in time to prevent cross-talks in a subsequent context where similar stimuli may need to be diﬀerently processed.”
Neurons as Monte Carlo Samplers: Bayesian Inference and Learning in Spiking Networks (2014, methodology): “The asymptotic convergence rate using only the filtered distribution is about one third the convergence rate obtained for the algorithms in [25] and [26], where the smoothed distribution is used.”