BI 110 Catherine Stinson and Jessica Thompson: Neuro-AI Explanation

July 06, 2021 01:25:02
BI 110 Catherine Stinson and Jessica Thompson: Neuro-AI Explanation
Brain Inspired
BI 110 Catherine Stinson and Jessica Thompson: Neuro-AI Explanation

Jul 06 2021 | 01:25:02

/

Show Notes

Catherine, Jess, and I use some of the ideas from their recent papers to discuss how different types of explanations in neuroscience and AI could be unified into explanations of intelligence, natural or artificial. Catherine has written about how models are related to the target system they are built to explain. She suggests both the model and the target system should be considered as instantiations of a specific kind of phenomenon, and explanation is a product of relating the model and the target system to that specific aspect they both share. Jess has suggested we shift our focus of explanation from objects – like a brain area or a deep learning model – to the shared class of phenomenon performed by those objects. Doing so may help bridge the gap between the different forms of explanation currently used in neuroscience and AI. We also discuss Henk de Regt’s conception of scientific understanding and its relation to explanation (they’re different!), and plenty more.

Timestamps:
0:00 – Intro
11:11 – Background and approaches
27:00 – Understanding distinct from explanation
36:00 – Explanations as programs (early explanation)
40:42 – Explaining classes of phenomena
52:05 – Constitutive (neuro) vs. etiological (AI) explanations
1:04:04 – Do nonphysical objects count for explanation?
1:10:51 – Advice for early philosopher/scientists

Other Episodes

Episode 0

January 15, 2019 01:09:27
Episode Cover

BI 024 Tim Behrens: Cognitive Maps

Show notes: Tim’s Neuroscience homepage: Follow Tim on Twitter: @behrenstim. Edward Tolman’s cognitive maps work: Cognitive maps in rats and men. Place Cells and...

Listen

Episode 0

June 24, 2020 01:16:03
Episode Cover

BI 075 Jim DiCarlo: Reverse Engineering Vision

Jim and I discuss his reverse engineering approach to visual intelligence, using deep models optimized to perform object recognition tasks. We talk about the...

Listen

Episode 0

December 26, 2021 01:18:59
Episode Cover

BI 123 Irina Rish: Continual Learning

Support the show to get full episodes and join the Discord community. Irina is a faculty member at MILA-Quebec AI Institute and a professor...

Listen