Friday Lecture Series
(open to the Rockefeller community)
Friday, November 5, 2021
Geoffrey E. Hinton, Ph.D.
Emeritus Professor,
Department of Computer Science, University of Toronto,
Vice President and Engineering fellow at Google,
Chief Scientific Adviser at the Vector Institute
How to Represent Part-whole Hierarchies in a Neural Net
Recommended Readings:
Empirical Articles
Qin, Y., Frosst, N., Sabour, S., Rael, C., Cottrell, C. and Hinton, G. (2020) Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions. ICLR-2020
Kosiorek, A. R., Sabour, S., Teh, Y. W. and Hinton, G. E. (2019) Stacked Capsule Autoencoders. Advances in Neural Information Processing Systems 32
Zhang, M., Lucas, J., Ba, J., and Hinton, G. E. (2019) Lookahead Optimizer: k steps forward, 1 step back. Advances in Neural Information Processing Systems 32
Muller, R., Kornblith, S. and Hinton G. (2019) When Does Label Smoothing Help? Advances in Neural Information Processing Systems 32
Kornblith, S., Norouzi, M., Lee, H. and Hinton, G. (2019) Similarity of neural network representations revisitedProceedings of the 36th International Conference on Machine Learning, 97:3519-3529, 2019
Hinton, G. E., Sabour, S. and Frosst, N. (2018) Matrix Capsules with EM Routing. ICLR-2018
