77 citations · 115 across the 4 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2016★ 28 cited
An Architecture for Deep, Hierarchical Generative Models
Philip Bachman
We present an architecture which lets us train deep, directed generative models with many layers of latent variables. We include deterministic paths between all latent variables an…
cs.LG2016★ 9 cited
Towards Information-Seeking Agents
Philip Bachman, Alessandro Sordoni, Adam Trischler
We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which succe…
cs.LG2014★ 1 cited
Representation as a Service
Ouais Alsharif, Philip Bachman, Joelle Pineau
Consider a Machine Learning Service Provider (MLSP) designed to rapidly create highly accurate learners for a never-ending stream of new tasks. The challenge is to produce task-spe…