Deep Learning, Language, and Code: From Methodology to Applications and Back

Slides, papers, code for talk by Charles Sutton

Slides

Slides as pdf

TL;CE (too long; checked email)

There are three main sections to the talk:

Papers

Deep Learning to Detect Redundant Method Comments. Annie Louis, Santanu Dash, Earl T Barr, and Charles Sutton. 2018

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning. Akash Srivastava, Lazar Valkov, Chris Russell, Michael Gutmann and Charles Sutton. Advances in Neural Information Processing Systems (NIPS) 2017.

Learning Continuous Semantic Representations of Symbolic Expressions. Miltiadis Allamanis, Pankajan Chanthirasegaran, Pushmeet Kohli and Charles Sutton. In Interational Conference on Machine Learning (ICML). 2017.

[ .pdf | bib ]

Synthesis of Differentiable Functional Programs for Lifelong Learning. Lazar Valkov, Dipak Chaudhari, Akash Srivastava, Charles Sutton, and Swarat Chaudhuri. arXiv 1804.00218

Visualizations and Data

Why am I doing this?

I’ve written a bit about the philosophy of these pages on my talks page.