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...
For many centuries, philosophers and scientists have pondered the origins and nature of human intuitions about the properties of points, lines, and figures on the Euclidean plane,...
We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalizatio...