Many perception and multimedia indexing problems involve datasets that are naturally comprised of multiple streams or modalities for which supervised training data is only sparsely...
Ashish Kapoor, Chris Mario Christoudias, Raquel Ur...
The recent explosion of on-line information in Digital Libraries and on the World Wide Web has given rise to a number of query-based search engines and manually constructed topica...
Mehran Sahami, Salim Yusufali, Michelle Q. Wang Ba...
We propose statistical predicate invention as a key problem for statistical relational learning. SPI is the problem of discovering new concepts, properties and relations in struct...
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
Abstract. A crucial problem in machine learning is to choose an appropriate representation of data, in a way that emphasizes the relations we are interested in. In many cases this ...