My work focuses on how children's rich theories of the world and sophisticated mental simulations are used to support action.
Key areas of interest include planning, tool use, and spatial reasoning.
A Task and Motion Approach to the Development of Planning
Developmental psychology presents us with a puzzle: though
children are remarkably apt at planning their actions, they suf-
fer from surprising yet consistent shortcomings. We argue that
these patterns of triumph and failure can be broadly captured
by the framework of task and motion planning, where plans
are hybrid entities consisting of both a structured, symbolic
skeleton and a continuous, low-level trajectory.
Learning constraint-based planning models from demonstrations
We present a framework for learning constraint-based task
and motion planning models using gradient descent. Our model
observes expert demonstrations of a task and decomposes them
into modes—segments which specify a set of constraints on
a trajectory optimization problem.
Discovering a symbolic planning language from continuous experience
We present a model that starts out with a language
of low-level physical constraints and, by observing expert
demonstrations, builds up a library of high-level concepts that
afford planning and action understanding.
Rearranging the Familiar: Testing Compositional Generalization in
EMNLP BlackboxNLP Workshop, 2018
We extend the study of systematic compositionality in seq2seq models
to settings where the model needs only to recombine well-trained functional words.
Our findings confirm and strengthen the earlier ones: seq2seq models can be impressively good at generalizing to novel combinations of previously-seen input, but only when
they receive extensive training on the specific
pattern to be generalized
Human Learning of Video Games
NIPS Workshop on Cognitively Informed Artificial Intelligence (Spotlight Talk), 2017
Work on human-level learning in Atari-like games, learning theories from gameplay and using them to plan in a model-based manner.
Decoding fMRI activity in the time domain improves classification performance
We show that fMRI decoding can be cast as a regression problem: fitting a design matrix with BOLD activation:
event classification is then easily obtained from the predicted design matrices.
Our experiments show this approach outperforms state of the art solutions, especially for designs with low inter-stimulus intervals,
and the two-step nature of the model brings time-domain interpretability.
Loading and plotting of cortical surface representations in Nilearn
Research Ideas and Operations, 2017
We present an initial support of cortical surfaces in Python within the neuroimaging data processing toolbox Nilearn.
We provide loading and plotting functions for different surface data formats with minimal dependencies, along with examples of their application.
Limitations of the current implementation and potential next steps are discussed.