Portrait of Doina Precup

Doina Precup

Core Academic Member
Canada CIFAR AI Chair
Associate Professor, McGill University, School of Computer Science
Research Team Leader, Google DeepMind
Research Topics
Medical Machine Learning
Molecular Modeling
Probabilistic Models
Reasoning
Reinforcement Learning

Biography

Doina Precup combines teaching at McGill University with fundamental research on reinforcement learning, in particular AI applications in areas of significant social impact, such as health care. She is interested in machine decision-making in situations where uncertainty is high.

In addition to heading the Montreal office of Google DeepMind, Precup is a Senior Fellow of the Canadian Institute for Advanced Research and a Fellow of the Association for the Advancement of Artificial Intelligence.

Her areas of speciality are artificial intelligence, machine learning, reinforcement learning, reasoning and planning under uncertainty, and applications.

Current Students

Collaborating Alumni - McGill University
Co-supervisor :
Collaborating Alumni - McGill University
PhD - McGill University
Co-supervisor :
PhD - McGill University
Principal supervisor :
Master's Research - McGill University
Principal supervisor :
Master's Research - McGill University
Co-supervisor :
Master's Research - McGill University
Master's Research - McGill University
PhD - McGill University
Collaborating Alumni - McGill University
Collaborating Alumni - McGill University
PhD - McGill University
Principal supervisor :
Master's Research - McGill University
Master's Research - McGill University
Principal supervisor :
Collaborating researcher - McGill University
Co-supervisor :
Research Intern - McGill University
PhD - McGill University
Principal supervisor :
Research Intern - McGill University
Master's Research - McGill University
Co-supervisor :
PhD - McGill University
Principal supervisor :
PhD - McGill University
Collaborating Alumni - McGill University
Co-supervisor :

Publications

Independently Controllable Factors
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it rema… (see more)ins an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that some of the causal factors could be discovered if the learner is allowed to interact with its environment. The agent can experiment with different actions and observe their effects. More specifically, we hypothesize that some of these factors correspond to aspects of the environment which are independently controllable, i.e., that there exists a policy and a learnable feature for each such aspect of the environment, such that this policy can yield changes in that feature with minimal changes to other features that explain the statistical variations in the observed data. We propose a specific objective function to find such factors and verify experimentally that it can indeed disentangle independently controllable aspects of the environment without any extrinsic reward signal.
Independently Controllable Features
A Matrix Splitting Perspective on Planning with Options
Smart Classifier Selection for Activity Recognition on Wearable Devices
Negar Ghourchian
Activity recognition is a key component of human-machine interaction applications. Information obtained from sensors in smart wearable devic… (see more)es is especially valuable, because these devices have become ubiquitous, and they record large amounts of data. Machine learning algorithms can then be used to process this data. However, wearable devices impose restrictions in terms of computation and energy resources, which need to be taken into account by a learning algorithm. We propose to use a real-time learning approach, which interactively determines the most effective set of modalities (or features) for classification, given the task at hand. Our algorithm optimizes sensor selection, in order to consume less power, while still maintaining good accuracy in classifying sequences of activities. Performance on a large, noisy dataset including four different sensing modalities shows that this is a promising approach.
Verb Phrase Ellipsis Resolution Using Discriminative and Margin-Infused Algorithms
Jackie CK Cheung
Verb Phrase Ellipsis (VPE) is an anaphoric construction in which a verb phrase has been elided. It occurs frequently in dialogue and informa… (see more)l conversational settings, but despite its evident impact on event coreference resolution and extraction, there has been relatively little work on computational methods for identifying and resolving VPE. Here, we present a novel approach to detecting and resolving VPE by using supervised discriminative machine learning techniques trained on features extracted from an automatically parsed, publicly available dataset. Our approach yields state-of-the-art results for VPE detection by improving F1 score by over 11%; additionally, we explore an approach to antecedent identifi-cation that uses the Margin-Infused-Relaxed-Algorithm, which shows promising results.
Prediction of Cell Type Specific Transcription Factor Binding Site Occupancy
Editorial on Special Issue on Probabilistic Models for Biomedical Image Analysis.
Manuel Jorge Cardoso
William M. Wells III
Albert C. S. Chung
Bayesian and grAphical Models for Biomedical Imaging
M. Jorge Cardoso
Ivor J. A. Simpson
Arbel, Tal
Annemie Ribbens
Assessing Generalization in TD methods for Deep Reinforcement Learning
Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces
We propose a general framework for policy representation for reinforcement learning tasks. This framework involves finding a low-dimensional… (see more) embedding of the policy on a reproducing kernel Hilbert space (RKHS). The usage of RKHS based methods allows us to derive strong theoretical guarantees on the expected return of the reconstructed policy. Such guarantees are typically lacking in black-box models, but are very desirable in tasks requiring stability. We conduct several experiments on classic RL domains. The results confirm that the policies can be robustly embedded in a low-dimensional space while the embedded policy incurs almost no decrease in return.