We present algorithms for coupling and training hidden Markov models (HMMs) to model interacting processes, and demonstrate their superiority to conventional HMMs in a vision task classifying two-handed actions. HMMs are perhaps the most successful framework in perceptual computing for modeling

It is a striking fact that in humans the greatest learnmg occurs precisely at that point in time- childhood- when the most dramatic maturational changes also occur. This report describes possible synergistic interactions between maturational change and the ability to learn a complex domain

-featured database systems and can answer only a small set of queries over their data (for example, forms on the WWW restrict the set of queries one can ask). (3) Since the number of sources is very large, effective techniques are needed to prune the set of information sources accessed to answer a query. (4

We report results on how the collabora-tive process of referring in task-oriented dialogue is affected by the restrictive in-teractivity of a turn-taking policy com-monly used in dialogue systems, namely push-to-talk. Our findings show that the restriction did not have a negative ef-fect. Instead

Generating action sequences to achieve a set of goals is a computationally difficult task. When multiple goals are present, the problem is even worse. Although many solutions to this problem have been discussed in the literature, practical solutions focus on the use of restricted mechanisms

Object-oriented programming languages allow inter-object aliasing. Although necessary to construct linked data structures and networks of interacting objects, aliasing is problematic in that an aggregate object's state can change via an alias to one of its components, without the aggregate

Regulation of the immune system has been shown (1) to result from complex interactions among subsets of lymphocytes and other cells. Some of these interactions are defined as genetically restricted when the effective interaction requires a certain identity among the cells involved. The genetic

We investigate the interactions of subtyping and recursive types, in a simply typed λ-calculus. The two fundamental questions here are whether two (recursive) types are in the subtype relation, and whether a term has a type. To address the first question, we relate various definitions of type

HMMER is a software suite for protein sequence similarity searches using probabilistic methods. Previously, HMMER has mainly been available only as a computationally intensive UNIX command-line tool, restricting its use. Recent advances in the soft-ware, HMMER3, have resulted in a 100-fold speed

up antigen and stimulate immune lymphocytes in an I-region-restricted interaction. They are strongly stimulatory in an allo-geneic primary mixed lymphocyte culture. Charac-terization of this cell type suggests potential new insights into the pathogenesis of renal allograft rejection