Nearly all general-purpose neural semantic parsers generate logical form...
Humans learn quickly even in tasks that contain complex visual informati...
AI planning and Reinforcement Learning (RL) both solve sequential
decisi...
This paper introduces an information-theoretic constraint on learned pol...
Biological agents learn and act intelligently in spite of a highly limit...
Compositional and relational learning is a hallmark of human intelligenc...
The difficulty of classical planning increases exponentially with search...
Compositionality is a key strategy for addressing combinatorial complexi...
A hallmark of human cognition is the ability to continually acquire and
...
Given the recent success of Deep Learning applied to a variety of single...
Deep lifelong learning systems need to efficiently manage resources to s...
A popular recent approach to answering open-domain questions is to first...
Multi-task learning (MTL) with neural networks leverages commonalities i...
In recent years researchers have achieved considerable success applying
...
In this paper we present a new dataset and user simulator e-QRAQ (explai...
We introduce the multiresolution recurrent neural network, which extends...