lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
Temporal information has been the focus of recent attention in information extraction, leading to some standardization effort, in particular for the task of relating events in a t...
Grammatical relationships are an important level of natural language processing. We present a trainable approach to find these relationships through transformation sequences and-e...
Given the uncertainty of the online environment, institutional trust is fundamental in building and retaining online interorganizational relationships. The authors propose two typ...
We derive an optimal learning rule in the sense of mutual information maximization for a spiking neuron model. Under the assumption of small fluctuations of the input, we find a s...