This paper proposes an initialization of back propagation (BP) networks for pattern classification problems; the weights of hidden units are initialized so that hyperplanes should...
The paper presents a framework called ECOS for Evolving COnnectionist Systems. ECOS evolve through incremental learning. They can accommodate any new input data, including new fea...
Most of recent and important algorithms in signal processing (for blind identification or separation, etc) are based on higher order statistics (HOS). And most of them use a crite...
Learning transfer is the improvement in performance on one task having learnt a related task. That the degree of transfer is signi cantly greater in humans than other primates and...
This paper describes a practical application of a novel terminal attractor algorithm to the construction of Perfect Hash Functions (PHF) for a prede ned set of keys. The proposed ...