Deep learning in the brain?

Summary

Date: 
April 23, 2019 - 12:00pm
Location: 
BioLabs Building, Room 1080
About the Speaker
Name: 
Timothy Lillicrap
Speaker Title: 
Staff Research Scientist
Speaker Affiliation: 
Google DeepMind

There has been rapid progress in the application of machine learning to difficult problems such as: voice and image recognition, playing video games from raw-pixels, controlling high-dimensional motor systems, and winning at the games of Go, Chess and Starcraft. These recent advances have been made possible by employing the backpropagation-of-error algorithm. This algorithm enables the delivery of detailed error feedback to adjust synaptic weights, which means that even large networks can be effectively trained. Whether or not the brain employs similar deep learning algorithms remains contentious; how it might do so remains a mystery. I will begin by reviewing advances in machine learning that highlight the importance of backprop for effectively learning complex behaviours. Then I will describe recent neuroscience evidence that suggests an increasingly complex picture of neurons and neural circuits. Taken together, these findings suggest new ways that deep learning algorithms might be implemented in cortical networks in the brain.