Model based learning systems usually face to a problem of forgetting as a result of the incremental learning of new instances. Normally, the systems have to re-learn past instances...
Methods for learning Bayesian networks can discover dependency structure between observed variables. Although these methods are useful in many applications, they run into computat...
Eran Segal, Dana Pe'er, Aviv Regev, Daphne Koller,...
As an extension of Bayesian network, module network is an appropriate model for inferring causal network of a mass of variables from insufficient evidences. However learning such ...
Reward-modulated spike-timing-dependent plasticity (STDP) has recently emerged as a candidate for a learning rule that could explain how local learning rules at single synapses su...
Robert A. Legenstein, Dejan Pecevski, Wolfgang Maa...