BI 088 Randy O'Reilly: Simulating the Human Brain

November 02, 2020 • 01:39:08
BI 088 Randy O'Reilly: Simulating the Human Brain
Brain Inspired
BI 088 Randy O'Reilly: Simulating the Human Brain

Nov 02 2020 | 01:39:08

/

Show Notes

Randy and I discuss his LEABRA cognitive architecture that aims to simulate the human brain, plus his current theory about how a loop between cortical regions and the thalamus could implement predictive learning and thus solve how we learn with so few examples. We also discuss what Randy thinks is the next big thing neuroscience can contribute to AI (thanks to a guest question from Anna Schapiro), and much more.

A few take-home points:

Timestamps:

0:00 –  Intro 
3:54 – Skip Intro 
6:20 – Being in awe 
18:57 – How current AI can inform neuro 
21:56 – Anna Schapiro question – how current neuro can inform AI.
29:20 – Learned vs. innate cognition 
33:43 – LEABRA 
38:33 – Developing Leabra 
40:30 – Macroscale
42:33 – Thalamus as microscale 
43:22 – Thalamocortical circuitry 
47:25 – Deep predictive learning 
56:18 – Deep predictive learning vs. backrop 
1:01:56 – 10 Hz learning cycle 
1:04:58 – Better theory vs. more data 
1:08:59 – Leabra vs. Spaun 
1:13:59 – Biological realism 
1:21:54 – Bottom-up inspiration 
1:27:26 – Biggest mistake in Leabra 
1:32:14 – AI consciousness 
1:34:45 – How would Randy begin again? 

Other Episodes

Episode 0

December 09, 2019 • 01:26:18
Episode Cover

BI 055 Thomas Naselaris: Seeing Versus Imagining

Thomas and I talk about what happens in the brain’s visual system when you see something versus imagine it. He uses generative encoding and...

Listen

Episode

February 19, 2019 • 01:14:09
Episode Cover

BI 028 Sam Gershman: Free Energy Principle & Human Machines

Show notes: Sam's Computational Cognitive Neuroscience Lab.Follow Sam on Twitter: @gershbrain.The papers we discuss: What does the free energy principle tell us about the...

Listen

Episode 0

August 28, 2019 • 01:16:52
Episode Cover

BI 045 Raia Hadsell: Robotics and Deep RL

Support the Podcast Show notes: Raia and I discuss her work at DeepMind figuring out how to build robots using deep reinforcement learning to...

Listen