Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this...
We present a method for parameter learning in relational Bayesian networks (RBNs). Our approach consists of compiling the RBN model into a computation graph for the likelihood fun...
Models of learning and performing by exploration assume that the semantic distance between task descriptions and screen labels controls in part the usersÕ search strategies. Neve...
- As an alternative to traditional Evolutionary Algorithms (EAs), Population-Based Incremental Learning (PBIL) maintains a probabilistic model of the best individual(s). Originally...
This paper investigates the problem ofautomatically learning declarative models of information sources available on the Internet. We report on ILA, a domain-independent program th...