An algorithm is presented for online learning of rotations. The proposed algorithm involves matrix exponentiated gradient updates and is motivated by the von Neumann divergence. T...
This paper demonstrates the generality of the hidden Markov model approach for exploratory sequence analysis by applying the methodology to study students' learning behaviors ...
We propose a compact, low power VLSI network of spiking neurons which can learn to classify complex patterns of mean firing rates on–line and in real–time. The network of int...
: This paper describes a research project that was carried out to determine and evaluate the learning environment customisations required to support selfmotivated, able, and experi...
Winner-Takes-All (WTA) prescriptions for Learning Vector Quantization (LVQ) are studied in the framework of a model situation: Two competing prototype vectors are updated accordin...