This work proposes a learning method for deep architectures that takes advantage of sequential data, in particular from the temporal coherence that naturally exists in unlabeled v...
Many recommendation and retrieval tasks can be represented as proximity queries on a labeled directed graph, with typed nodes representing documents, terms, and metadata, and labe...
— This paper proposes an approach allowing indoor environment supervised learning to recognize relevant features for environment understanding. Stochastic preprocessing methods i...
Variational Bayesian (VB) methods are typically only applied to models in the conjugate-exponential family using the variational Bayesian expectation maximisation (VB EM) algorith...
Antti Honkela, Tapani Raiko, Mikael Kuusela, Matti...
The eligibility trace is one of the most used mechanisms to speed up reinforcement learning. Earlier reported experiments seem to indicate that replacing eligibility traces would p...