Résumé - James Cook

I am a dual ctizen of Canada and the United states.

Education: UC Berkeley

I have been a Ph.D. student in computer science (theory) since September 2007.

Education: University of Toronto

Honours Bachelor of Science, specializing in Computer Science and Mathematics, completed May 2007. CGPA 3.86 out of 4.

Research Experience

Conference Paper (AISTATS 2007)

James Cook, Ilya Sutskever, Andriy Mnih and Geoffrey Hinton, "Visualising Similarity Data with a Mixture of Maps". Abstract:

We show how to visualize a set of pairwise similarities between objects by using several different two-dimensional maps, each of which captures different aspects of the similarity structure. When the objects are ambiguous words, for example, different senses of a word occur in different maps, so ``river'' and ``loan'' can both be close to ``bank'' without being at all close to each other. Aspect maps resemble clustering because they model pair-wise similarities as a mixture of different types of similarity, but they also resemble local multi-dimensional scaling because they model each type of similarity by a two-dimensional map. We demonstrate our method on a toy example, a database of human word-association data, a large set of images of handwritten digits, and a set of feature vectors that represent words.

Work Experience

Summer 2007: Software Engineering Intern at Google. I worked on a large software project in C++, and wrote my own piece of software in JavaScript.

Technical Skills

Dance, Music, Drama

Contact Information

E-Mail: jcook@eecs.berkeley.edu; Phone: 510-221-7496; Website: http://www.falsifian.org/