We focus on methods to solve multiclass learning problems by using only simple and efficient binary learners. We investigate the approach of Dietterich and Bakiri [2] based on er...
This paper investigates a mechanism for reliable generation of sparse code in a sparsely connected, hierarchical, learning memory. Activity reduction is accomplished with local com...
— Chuck is a new code browser that allows navigation of a code base along semantic structures, such as data-flow and higher-order control-flow relationships. Employing the fast...
This paper explores in detail the use of Error Correcting Output Coding (ECOC) for learning text classifiers. We show that the accuracy of a Naive Bayes Classifier over text class...
Recent studies have argued that natural vision systems perform classification by utilizing different mechanisms depending on the visual input. In this paper we present a hybrid, ...