Existing work on programmable self assembly has focused on deterministic performance guarantees--stability of desirable states. In particular, for any acyclic target graph a binary...
We introduce a general-purpose learning machine that we call the Guaranteed Error Machine, or GEM, and two learning algorithms, a real GEM algorithm and an ideal GEM algorithm. Th...
We describe a cognitive architecture for creating more robust intelligent systems by executing hybrids of algorithms based on different computational formalisms. The architecture ...
Nicholas L. Cassimatis, Perrin G. Bignoli, Magdale...
The structural properties of graphs are usually characterized in terms of invariants, which are functions of graphs that do not depend on the labeling of the nodes. In this paper ...
Venkat Chandrasekaran, Pablo A. Parrilo, Alan S. W...
We conduct a series of Part-of-Speech (POS) Tagging experiments using Expectation Maximization (EM), Variational Bayes (VB) and Gibbs Sampling (GS) against the Chinese Penn Treeba...