17:I[66739,["/_next/static/chunks/0.3dg.jzl0xwf.js?dpl=dpl_Hst3gh7MhZkzS6iaknkgT6LpsCH8","/_next/static/chunks/0skdv12y78fnh.js?dpl=dpl_Hst3gh7MhZkzS6iaknkgT6LpsCH8","/_next/static/chunks/10dnvbzcepzg2.js?dpl=dpl_Hst3gh7MhZkzS6iaknkgT6LpsCH8","/_next/static/chunks/0w-9dtq49e_fk.js?dpl=dpl_Hst3gh7MhZkzS6iaknkgT6LpsCH8","/_next/static/chunks/1331nw5i_3lcb.js?dpl=dpl_Hst3gh7MhZkzS6iaknkgT6LpsCH8","/_next/static/chunks/053zyoym-_i67.js?dpl=dpl_Hst3gh7MhZkzS6iaknkgT6LpsCH8"],"default"] 19:I[38632,["/_next/static/chunks/0qqtp3r0h7kah.js?dpl=dpl_Hst3gh7MhZkzS6iaknkgT6LpsCH8","/_next/static/chunks/0iukvycbd42rl.js?dpl=dpl_Hst3gh7MhZkzS6iaknkgT6LpsCH8"],"IconMark"] 18:T402,

This week Dr. Tim Scarfe and Dr. Keith Duggar discuss Explainability, Reasoning, Priors and GPT-3. We check out Christoph Molnar's book on intepretability, talk about priors vs experience in NNs, whether NNs are reasoning and also cover articles by Gary Marcus and Walid Saba critiquing deep learning. We finish with a brief discussion of Chollet's ARC challenge and intelligence paper.

00:00:00 Intro

00:01:17 Explainability and Christoph Molnars book on Intepretability

00:26:45 Explainability - Feature visualisation

00:33:28 Architecture / CPPNs

00:36:10 Invariance and data parsimony, priors and experience, manifolds

00:42:04 What NNs learn / logical view of modern AI (Walid Saba article)

00:47:10 Core knowledge

00:55:33 Priors vs experience

00:59:44 Mathematical reasoning

01:01:56 Gary Marcus on GPT-3

01:09:14 Can NNs reason at all?

01:18:05 Chollet intelligence paper/ARC challenge

Explainability, Reasoning, Priors and GPT-3

Machine Learning Street Talk (MLST)

Explainability, Reasoning, Priors and GPT-3