The model here proposed simulates the development of the object recognition capability, assuming that recognition does not imply any sort of explicit geometrical reconstruction and...
We describe a kernel method which uses the maximization of Onicescu’s informational energy as a criteria for computing the relevances of input features. This adaptive relevance d...
Abstract. Dynamic neural filters (DNFs) are recurrent networks of binary neurons. Under proper conditions of their synaptic matrix they are known to generate exponentially large c...
We present an approach where we combine attention with value maps for the purpose of acquiring a decision-making policy for multiple concurrent goals. The former component is essen...
We report results of an interdisciplinary project which aims at endowing a real robot system with the capacity for learning by goaldirected imitation. The control architecture is b...
Wolfram Erlhagen, Albert Mukovskiy, Estela Bicho, ...