Machine Learning Street Talk (MLST)

Explainability, Reasoning, Priors and GPT-3

Sep 16, 2020

Dr. Keith Duggar, MIT PhD and AI expert, joins for a captivating discussion on explainability in machine learning. They dive into Christoph Molnar's insights on interpretability and the intricacies of neural networks' reasoning. Duggar contrasts priors with experience, touches on core knowledge, and critiques deep learning through notable figures like Gary Marcus. The conversation culminates in exploring ethical implications and challenges of GPT-3's reasoning, highlighting the broader questions of machine intelligence and the future of AI.

01:25:52

Creator website

Episode guests

Keith Duggar

AI Chapters

Episode notes

Intro

5min

Understanding Model Explainability

11min

Human Biases vs. Machine Learning

4min

Understanding Explainability in Machine Learning

18min

Challenges in CNNs and Knowledge Representation

21min

Navigating Language and Math in Machine Learning

4min

Critiques of Deep Learning and AI Ethics

3min

Limitations of AI Reasoning

12min

Unpacking Neural Network Reasoning and Intelligence Challenges

3min

10.

Rethinking Intelligence: Transformational Learning

5min

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

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.