Email: jsnell [at] cs [dot] toronto [dot] edu
Curriculum vitae (last updated: Jun 2018).
(June 2019) I recently married my wonderful wife, Kyeonga Kong. We celebrated our eternal love with two wedding ceremonies: an American ceremony in May (Maryland, USA) and a Korean ceremony in June (Gwangju, South Korea). Kyeonga: I pray for many happy and healthy years together with you. Words cannot express how grateful I am to be your husband. Thank you for being my wife and for your support every day. I love you. ❤
My research interests lie primarily in few-shot learning, metric learning, and generative modeling. In the past I've also worked on structured output learning and image segmentation.
My supervisor is Rich Zemel.
Dimensionality Reduction for Representing the Knowledge of Probabilistic Models
Marc T. Law, Jake Snell, Amir-Massoud Farahmand, Raquel Urtasun & Richard Zemel. (ICLR 2019)
[pdf] [code: visualization, zero-shot learning 1 2]
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]
Summer 2016: Twitter with Kevin Swersky (Cambridge, MA)