We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Hand-coded scripts were used in the 1970-80s as knowledge backbones that enabled inference and other NLP tasks requiring deep semantic knowledge. We propose unsupervised induction...
Video document retrieval is now an active part of the domain of multimedia retrieval. However, unlike for other media, the management of a collection of video documents adds the pr...
This paper adds temporal logic to public announcement logic (PAL) and dynamic epistemic logic (DEL). By adding a previous-time operator to PAL, we express in the language statemen...
We present an approach for recognition and clustering of spatio temporal patterns based on networks of spiking neurons with active dendrites and dynamic synapses. We introduce a n...