- Machine learning
- Deep learning
- Unsupervised learning
- Computer vision
- Hardware acceleration
- Time series
Graham Taylor is a Professor of Engineering at the University of Guelph, a CIFAR Azrieli Global Scholar, an Academic Director of NextAI, Interim Research Director and a Faculty Member of the Vector Institute for Artificial Intelligence. His research aims to discover new algorithms and architectures for deep learning: the automatic construction of hierarchical algorithms from high-dimensional, unstructured data. He is especially interested in time series, having applied his work to better understand human and animal behaviour, environmental data (climate or agricultural), audio (music or speech) and financial time series. His work also intersects high performance computing, investigating better ways to leverage hardware accelerators to cope with the challenges of large-scale machine learning. He co-organizes the annual CIFAR Deep Learning Summer School, and has trained more than 50 students and staff members on AI-related projects.
- 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.
- CIFAR Azrieli Global Scholar (2016). Award is based on research excellence and leadership.
- Secured more than $2.4M in external funding from government and private sources, including Amazon, Google, and Huawei.
- In 2016, received a highly competitive NSERC-French National Research Agency Strategic Partnerships Grant to carry out collaborative research with 6 different labs in Canada and France.
- Judge for the AI X-PRIZE which challenges teams globally to develop and demonstrate how humans can collaborate with powerful AI technologies to tackle the world’s grand challenges.
- Senior Program Committee member for the premiere machine learning conference: Neural Information Processing Systems and the emerging International Conference on Learning Representations.
Research Activity and News
- CIFAR Azrieli Global Scholar Profile: How Graham Taylor champions AI innovation & entrepreneurship
- Podcast: Learning to Learn, and other Opportunities in Machine Learning with Graham Taylor
- Guelph Life: The Human Side of Machine Learning
- Terrance Devries and Graham Taylor. Learning confidence for out-of-distribution detection in neural networks. arXiv preprint arXiv:1802.04865, 2018.
- Angus Galloway, Graham Taylor, and Medhat Moussa. Attacking binarized neural networks. In International Conference on Learning Representations (ICLR), 2018.
- Natalia Neverova, Christian Wolf, Griffin Lacey, Lex Fridman, Deepak Chandra, Brandon Barbello, and Graham Taylor. Learning human identity from motion patterns. IEEE Access, 4:1810–1820, 2016.