Many researchers have used lexical networks and ontologies to mitigate synonymy and polysemy problems in Question Answering (QA), systems coupled with taggers, query classifiers,...
The development of flexible and reusable concurrent object-oriented programming ions has suffered from the inherent problem that reusability and extensibility is limited due to pos...
The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product o...
In recent years, compositional modeling and selfexplanatory simulation techniques have simplified the process of building dynamic simulators of physical systems. Building steady-s...
We present a new algorithm for eliminating excess parameters and improving network generalization after supervised training. The method, \Principal Components Pruning (PCP)",...