: We present the implementation of on-line Hebbian learning for NESPINN, the Neurocomputer for the simulation of spiking neurons. In order to support various forms of Hebbian learn...
Realistic domains for learning possess regularities that make it possible to generalize experience across related states. This paper explores an environment-modeling framework tha...
— Parallel algorithms are presented for modules of learning automata with the objective of improving their speed of convergence without compromising accuracy. A general procedure...
Active learning has been applied to different NLP tasks, with the aim of limiting the amount of time and cost for human annotation. Most studies on active learning have only simul...
The Information Fusion Panel within The Technical Cooperation Program (TTCP) is developing algorithms to perform machine-based situation assessment to assist human operators in co...