What can artificial neural networks teach us about our own brains?

I interview Patrick Mineault, an independent scientist working at the intersection of neuroscience and deep learning. On his famous blog xcorr.net, he writes about the rapidly accelerating merger of techniques in AI and neuroscience. This field - neuroAI - aims to study how the brain works by studying artificial neural networks.

Patrick did his PhD in visual neuroscience from McGill University. He has worked at Google as a scientist and then worked with Facebook to build brain-machine interfaces. Most recently, he has helped build Neuromatch Academy, an online summer school on computational neuroscience.

== What we talk about ==
0:00 - Introduction
1:27 - How do you define neuroAI?
4:10 - What does ‘"understanding" something even mean?
14:20 - Are there any recent cases of neuroscience learning from deep learning/AI?
23:12 - Why have the evolution-inspired methodologies not been able to match the performance of straightforward deep learning models like GPT-3?
28:33 - How can unsupervised and supervised learning methods have similar performance in modeling the brain’s vision system?
36:50 - The difference between the amount of data given to process to supervised model vs unsupervised models
43:10 - Is anyone trying to model AI embedded in a 3D environment like we are?
51:15 - Do you think neuroAI can lead us to understand consciousness much more scientifically?
55:58 - Is anyone attempting to model consciousness in an artificial network?

== Useful links ==
Patrick's blog: https://xcorr.net