We show how the regularizer of Transductive Support Vector Machines (TSVM) can be trained by stochastic gradient descent for linear models and multi-layer architectures. The resul...
Michael Karlen, Jason Weston, Ayse Erkan, Ronan Co...
We built a text-based programming environment that enables youth to design and implement a chat client for the One Laptop per Child XO. The environment allows users to program and...
Abstract. Traditionally, software development teams follow Tayloristic approaches favoring division of labor and, hence, the use of role-based teams. Role-based teams require the t...
We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to ...
Ben Taskar, Dan Klein, Mike Collins, Daphne Koller...
We implement statically-typed multi-holed contexts in OCaml using an underlying algebraic datatype augmented with phantom types. Existing approaches require dynamic checks or more...