Jake Snell


PhD Candidate
Machine Learning Group
Department of Computer Science
University of Toronto, Vector Institute

Email: jsnell [at] cs [dot] toronto [dot] edu

Curriculum vitae (last updated: Jun 2018).

I am currently away for an internship from September - December 2018 at SK T-Brain in Seoul, South Korea.

Publications

Learning Latent Subspaces in Variational Autoencoders
Jack Klys, Jake Snell & Richard Zemel. (NIPS 2018)

Meta-Learning for Semi-Supervised Few-Shot Classification
Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Josh B. Tenenbaum, Hugo Larochelle & Richard Zemel. (ICLR 2018)
[pdf] [arxiv] [code]

Prototypical Networks for Few-Shot Learning
Jake Snell, Kevin Swersky & Richard Zemel. (NIPS 2017)
[pdf] [supplementary] [code]

Stochastic Segmentation Trees for Multiple Ground Truths
Jake Snell & Richard Zemel. (UAI 2017)
[pdf] [supplementary]

Learning to Generate Images with Perceptual Similarity Metrics
Jake Snell, Karl Ridgeway, Renjie Liao, Brett Roads, Michael C. Mozer & Richard Zemel. (ICIP 2017)
[pdf] [supplementary]

Research

My research interests lie primarily in deep learning, few-shot learning and generative modeling. In the past I've also worked on structured output learning and image segmentation.

My supervisor is Rich Zemel.