Graham Taylor is a Professor of Engineering at the University of Guelph, a Canada CIFAR AI Chair, an Academic Director of NextAI, and a Faculty Member of the Vector Institute for Artificial Intelligence. His research spans a number of topics in deep learning. He is interested in open problems such as how to effectively learn with less labeled data, and how to build human-centred AI systems. He is interested in methodologies such as generative modelling, graph representation learning and sequential decision making. He also pursues applied projects with global impact: such as using computer vision to mitigate biodiversity loss. He co-organizes the annual CIFAR Deep Learning Summer School, and has trained more than 80 students and staff members on AI-related projects.
Canada CIFAR Artificial Intelligence Chair
Academic Director, NextAI
Highlights
- Co-founded Kindred, which was featured at number 29 on MIT Technology Review’s 2017 list of smartest companies in the world and CB Insights AI 100 list, highlighting the most innovative artificial intelligence companies for 2018. The Narwhal List (University of Toronto Impact Centre) named it as the 9th fastest growing technology company in Canada. In 2018, Kindred received a Canadian Innovation Award in the Manufacturing & Robotics category. Kindred was acquired by the Ocado group in 2020.
- Holds a Tier 2 Canada Research Chair in Machine Learning.
- Founded and co-directs the University of Guelph Centre for Advancing Responsible and Ethical Artificial Intelligence (AI).
- Serves as Senior Area Chair at premiere machine learning conferences: Neural Information Processing Systems (NeurIPS) and the International Conference on Machine Learning (ICML). Serves as Area Chair at the International Conference on Learning Representations.
- Awarded Canada’s Top 40 under 40 (2019), an annual recognition of the exceptional achievements of outstanding, young Canadian leaders.
- Appointed as Google Visiting Faculty (2018-2019).
- Honoured as CIFAR Azrieli Global Scholar (2016). Award is based on research excellence and leadership.
Publications
Federated learning and differential privacy for medical image analysis
2022
Bulk arthropod abundance, biomass and diversity estimation using deep learning for computer vision
2022
On evaluation metrics for graph generative models
2022
Similarity learning networks for animal individual re-identification: an ecological perspective
2022
Predicting dreissenid mussel abundance in nearshore waters using underwater imagery and deep learning
2022
Facilitating robotic control using a virtual reality interface
2023
The gist and rist of iterative self-training for semi-supervised segmentation
2022
Learning with Less Labels in Digital Pathology Via Scribble Supervision from Natural Images
2022
Monitoring Shortcut Learning using Mutual Information
2023
Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers
2023
GCNet: Probing Self-Similarity Learning for Generalized Counting Network
2023
Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition
2023
Getting the Bugs Out: Entomology Using Computer Vision
2022
Bounding generalization error with input compression: An empirical study with infinite-width networks
2022
Understanding the impact of image and input resolution on deep digital pathology patch classifiers
2022
Understanding the impact of image and input resolution on deep digital pathology patch classifiers
2022
DeepRNG: Towards Deep Reinforcement Learning-Assisted Generative Testing of Software
2022
