The principle of maximizing mutual information is applied to learning overcomplete and recurrent representations. The underlying model consists of a network of input units driving...
In this paper we describe a new technique for parsing free text: a transformational grammar I is automatically learned that is capable of accurately parsing text into binary-branc...
A constraint satisfaction problem, or CSP, can be reformulated as an integer linear programming problem. The reformulated problem can be solved via polynomial multiplication. If t...
Abstract. A new dictionary learning method for exact sparse representation is presented in this paper. As the dictionary learning methods often iteratively update the sparse coeffi...
We are interested in learning programs for multiple related tasks given only a few training examples per task. Since the program for a single task is underdetermined by its data, ...