Last week, E. Laurence and I attended the NIPS 2014 workshop session in Montreal, Québec, Canada.

Surya Ganguli gave an excellent talk on deep learning ideas derived from statistical physics. As a “community detection” guy, I found the Networks Science Workshop especially interesting. Half of the invited speakers presented recent results in that area of network science. There was, two particularly noteworthy talks.

Liza Levina introduced a overlapping spectral detection algorithm, and Cristopher Moore showed us how the ideas of statistical mechanics can be used to better understand community detection.

The accepted papers can be found on the workshop page.