Blake Richards
Appointment
Fellow
Canada CIFAR AI Chair
National Program Committee member
Learning in Machines & Brains
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2019
Renewed Canada CIFAR AI Chair – 2024
Blake Richards’ research is at the intersection of neuroscience and AI. His laboratory investigates universal principles of intelligence that apply to both natural and artificial agents. This includes work on predictive learning, memory systems, and bio-inspired networks.
Awards
- Arthur B. McDonald Fellowship, NSERC, 2022
- NSERC Discovery Accelerator Supplement, 2020
- Young Investigator Award, Canadian Association for Neuroscience, 2019
- Ontario Early Researcher Award, 2018
- Google Faculty Research, 2016
Relevant Publications
- Azabou, M., et al. (2024). A unified, scalable framework for neural population decoding. Advances in Neural Information Processing Systems, 36.
- Kalajdzievski, D., Mao, X., Fortier-Poisson, P., Lajoie, G., & Richards, B. (2023). Transfer Entropy Bottleneck: Learning Sequence to Sequence Information Transfer. Transactions in Machine Learning Research.
- Zadort, A., et al. (2023). Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution. Nature Communications, 14: 1597.
- Pogodin, R., Cornford, J., Ghosh, A., Gidel, G., Lajoie, G., & Richards, B.A. (2023). Synaptic Weight Distributions Depend on the Geometry of Plasticity" In The Twelfth International Conference on Learning Representations.
- Agrawal, K.K., Mondal, A.K., Ghosh, A., & Richards, B. (2022). $\alpha $-ReQ: Assessing Representation Quality in Self-Supervised Learning by measuring eigenspectrum decay. Advances in Neural Information Processing Systems, 35, 17626-17638.
- Richards, B. A., Lillicrap, T. P., Beaudoin, P., Bengio, Y., Bogacz, R., Christensen, A., ... & Kording, K. P. (2019). A deep learning framework for neuroscience. Nature neuroscience, 22(11), 1761-1770.
Bartunov, S., A. Santoro, B.A. Richards, G.E. Hinton and T.P. Lillicrap (2018) “Assessing the scalability of biologically-motivated deep learning algorithms and architectures.” Neural Information Processing Systems.