Relations and Predictions in Brains and Machines

Add to your list(s) Download to your calendar using vCal

• Dr. Kim Stachenfeld, Deep Mind
• Thursday 02 March 2023, 15:00-16:00
• Online.

If you have a question about this talk, please contact Sofia Orellana.

Humans and animals learn and plan with flexibility and efficiency well beyond that of modern Machine Learning methods. This is hypothesized to owe in part to the ability of animals to build structured representations of their environments, and modulate these representations to rapidly adapt to new settings. In the first part of this talk, I will discuss theoretical work describing how learned representations in hippocampus enable rapid adaptation to new goals by learning predictive representations, while entorhinal cortex compresses these predictive representations with spectral methods that support smooth generalization among related states. I will also cover recent work extending this account, in which we show how the predictive model can be adapted to the probabilistic setting to describe a broader array of generalization results in humans and animals, and how entorhinal representations can be modulated to support sample generation optimized for different behavioral states. In the second part of the talk, I will overview some of the ways in which we have combined many of the same mathematical concepts with state-of-the-art deep learning methods to improve efficiency and performance in machine learning applications like physical simulation, relational reasoning, and design.

This talk is part of the Making connections- brains and other complex systems series.

This talk is included in these lists:

• Biology
• Cambridge Neuroscience Seminars
• Cambridge talks
• Chris Davis' list
• Featured lists
• Life Science
• Life Sciences
• Making connections- brains and other complex systems
• Neuroscience
• Neuroscience Seminars
• Neuroscience Seminars
• Online
• Stem Cells & Regenerative Medicine
• dh539

Note that ex-directory lists are not shown.