In 2008, Collobert and Weston analyzed 2500 english words using deep neural nets. Since then, people like Joseph Turian have used technology such as t-SNE to visualize these results in a way that humans can actually comprehend (2 dimensions instead of thousands). This talk explores a naive Clojure programmer’s attempt to reproduce Turian’s word map of Collobert and Weston’s word feature vectors in pure Clojure from the raw sentences data set. Attendees will walk away with the contextual understanding and basic toolset to reproduce this study.
At the age of two, Alex disassembled his grandparent’s mechanical alarm clock. He has never put it back together. One of his most prized possessions is a slide rule. While attending the University of Toronto he did his best to avoid any practical courses and stuck to theory. It was there he learned Scheme/LISP. When he’s not cooking, climbing, or taming his pitbull, you can find him talking at Meetups or hacking away on some new project.