Eric Crawford E

Eric Crawford

Ottawa, Ottawa

This professional is in active search of jobs

About me:

Hi! I’m Eric, and I’m a PhD student in the Reasoning and Learning Lab at McGill University, supervised by Joelle Pineau.

I’m interested in many areas of machine learning and cognitive science, but recently my main focus has been on object discovery. More concretely, I’ve focused on how to build deep probabilistic neural networks that can learn to detect and track objects in the visual stream without supervision. I’ve built systems that can discover objects in images, videos, and, most recently, 3D worlds. I’m also interested in how to build systems that can reason in terms of objects in ways that exploit their compositionality.

In 2014 I completed a Masters degree in Computer Science in the Computational Neuroscience Research Group at the University of Waterloo. I was supervised by Chris Eliasmith, and worked on a biologically plausible model of human knowledge representation. I also wrote an MPI implementation of the nengo neural simulator. In 2012 I obtained a BMATH(CS) degree, also from Waterloo, and spent my co-op terms working on a GPU implementation of nengo.

When not working I like to travel, hike, play sports (squash, running and ultimate currently), play board games, and read books, especially sci-fi and non-fiction. My favorite authors are Kim Stanley Robinson, Neal Stephenson, Greg Egan, and Dan Dennett.

Education:

Candidate for PhD, Computer Science
MCGILL UNIVERSITY / MILA
Montreal, Quebec, Canada
2014-Aug 2021
• Cumulative GPA: 4.0/4.0
• Member of Reasoning and Learning Lab

Master of Mathematics, Computer Science
UNIVERSITY OF WATERLOO
Waterloo, Ontario, Canada
2012-2014
• Cumulative GPA: 91.80%
• Member of Computational Neuroscience Research Group

Bachelor of Mathematics, Honors Computer Science, Co-op, CogSci Option
UNIVERSITY OF WATERLOO
Waterloo, Ontario, Canada
2007-2012
• Cumulative GPA: 88.07%
• Dean's Honors List with Distinction

Experience:

Computer Vision Intern
UNITY TECHNOLOGIES
Vancouver, British Columbia, Canada
May 2021-Aug 2021
• Performed large-scale experiments aimed at finding opportunities for training instance segmentation networks on simulated data.
• Developed techniques for training Mask-RCNN on simulated data, aiming to reduce the number of hand-labeled examples required.
• Implemented robust and scalable infrastructure for managing large numbers of simultaneous training jobs using Google Cloud Platform.

Machine Learning Consultant
PERSONA IDENTITIES INC.
San Francisco, California, USA
2019
• Developed cloud-based deep learning capabilities for document verification using TensorFlow and Google Cloud Platform.
• Designed and implemented deep computer vision solutions enabling new forms of document verification.
• Performed extensive model selection and hyperparameter tuning to find the optimal balance between inference speed, precision and recall.

Lead Developer
COMPUTATIONAL NEUROSCIENCE RESEARCH GROUP, UNIVERSITY OF WATERLOO
Waterloo, Ontario, Canada
2010-2014
• Designed and implemented CUDA and MPI backends for the Nengo neural simulation package.
• Reduced network simulation times by several orders of magnitude using high-performance clusters, allowing
networks containing hundreds of thousands of neurons to be simulated in real-time.

Research Assistant
DEPARTMENT OF OTORHINOLARYNGOLOGY, UNIVERSITY OF PENNSYLVANIA
Philadelphia, Pennsylvania, USA
2011
• Implemented computational methods for identifying neural receptive fields based on neurophysiological data.

Developer
ACRONYM SOFTWARE
Waterloo, Ontario, Canada
2009
• Implemented UI features for wood and masonry engineering software in C++ and C#.

0 external recommendations