We describe an architecture for representing and managing context shifts that supports dynamic data interpretation. This architecture utilizes two layers of learning and three lay...
Nikita A. Sakhanenko, George F. Luger, Carl R. Ste...
When simple parametric models such as linear regression fail to adequately approximate a relationship across an entire set of data, an alternative may be to consider a partition o...
Hugh A. Chipman, Edward I. George, Robert E. McCul...
We describe a directed bilinear model that learns higherorder groupings among features of natural images. The model represents images in terms of two sets of latent variables: one...
Jack Culpepper, Jascha Sohl-Dickstein, Bruno Olaha...
We introduce a novel mechanism for incorporating articulatory dynamics into speech recognition with the theory of task dynamics. This system reranks sentencelevel hypotheses by th...
A neural network model that can simulate the learning of some simple proportional analogies is presented. These analogies include, for example, (a) red-square:red-circle yellow-sq...