Metonymy recognition is generally approached with complex algorithms that rely heavily on the manual annotation of training and test data. This paper will relieve this complexity ...
In some environments, a learning agent must learn to balance competing objectives. For example, a Q-learner agent may need to learn which choices expose the agent to risk and whic...
When constructing a Bayesian network, it can be advantageous to employ structural learning algorithms to combine knowledge captured in databases with prior information provided by...
Traditional single-agent search algorithms usually make simplifying assumptions (single search agent, stationary target, complete knowledge of the state, and sufficient time). The...
Mark Goldenberg, Alexander Kovarsky, Xiaomeng Wu, ...
We propose an algorithm for function approximation that evolves a set of hierarchical piece-wise linear regressors. The algorithm, named HIRE-Lin, follows the iterative rule learn...