— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...
The performance of many supervised and unsupervised learning algorithms is very sensitive to the choice of an appropriate distance metric. Previous work in metric learning and ada...
Adaptivity, both of the individual agents and of the interaction structure among the agents, seems indispensable for scaling up multi-agent systems MAS's in noisy environme...
David Wolpert, Sergey Kirshner, Christopher J. Mer...
This paper describes a networked FPGA-based implementation of the FAST (Flexible Adaptable-Size Topology) architecture, a Arti cial Neural Network (ANN) that dynamically adapts it...
A large body of research has investigated the advantages of combining phenotype adaptation and genotype adaptation. The hybridization of genetic search and local search methods, of...