In this paper, we introduce a new class of data mining problems called learning from aggregate views. In contrast to the traditional problem of learning from a single table of tra...
Bee-Chung Chen, Lei Chen 0003, Raghu Ramakrishnan,...
We describe a system that successfully transfers value function knowledge across multiple subdomains of realtime strategy games in the context of multiagent reinforcement learning....
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...
Learning to understand a single causal system can be an achievement, but humans must learn about multiple causal systems over the course of a lifetime. We present a hierarchical B...
Charles Kemp, Noah D. Goodman, Joshua B. Tenenbaum
We present a novel probabilistic multiple cause model for binary observations. In contrast to other approaches, the model is linear and it infers reasons behind both observed and ...