Published Apr 1, 2024

Dr. Paul Lessard - Categorical/Structured Deep Learning

Dr. Paul Lessard delves into the power of category theory and abstraction in transforming AI systems by improving neural networks' reasoning and generalization abilities, offering new perspectives on programming structures and computation.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

#60 Geometric Deep Learning Blueprint (Special Edition)
Answers 383 questions
Prof. Chris Bishop's NEW Deep Learning Textbook!
Answers 383 questions
#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
Answers 383 questions
#51 Francois Chollet - Intelligence and Generalisation
Answers 383 questions
#114 - Secrets of Deep Reinforcement Learning (Minqi Jiang)
Answers 383 questions
#50 Christian Szegedy - Formal Reasoning, Program Synthesis
Answers 383 questions
Mahault Albarracin - Cognitive Science
Answers 383 questions
It's Not About Scale, It's About Abstraction - Francois Chollet
Answers 383 questions
ICLR 2020: Yoshua Bengio and the Nature of Consciousness
Answers 383 questions
Francois Chollet - On the Measure of Intelligence
Answers 383 questions
Francois Chollet - ARC reflections - NeurIPS 2024
Answers 383 questions
MLST #78 - Prof. NOAM CHOMSKY (Special Edition)
Answers 383 questions
Understanding Deep Learning - Prof. SIMON PRINCE [STAFF FAVOURITE]
Answers 383 questions
#65 Prof. PEDRO DOMINGOS [Unplugged]
Answers 383 questions
MULTI AGENT LEARNING - LANCELOT DA COSTA
Answers 383 questions

Dexa/Machine Learning Street Talk (MLST)

Dr. Paul Lessard - Categorical/Structured Deep Learning

Topics covered

Popular Clips

Abstracting Mathematical Structures

Monad Magic Unveiled

Geometric Deep Learning

Data vs. Algorithms

Category Theory Applications

Neural Network Reasoning

Abstraction in Neural Networks

Category Theory Insights

Syntax and Semantics

Understanding Endofunctors

Neural Network Evolution

Category Theory Basics

Monad Structure Interpretation

Limitations of Language Models

Natural Transformations Unveiled

Episode Highlights

Abstraction and Semantics

Neural Networks and Computation

Category Theory Insights

Related Episodes

#60 Geometric Deep Learning Blueprint (Special Edition)

Prof. Chris Bishop's NEW Deep Learning Textbook!

#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]

#51 Francois Chollet - Intelligence and Generalisation

#114 - Secrets of Deep Reinforcement Learning (Minqi Jiang)

#50 Christian Szegedy - Formal Reasoning, Program Synthesis

Mahault Albarracin - Cognitive Science

It's Not About Scale, It's About Abstraction - Francois Chollet

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

Francois Chollet - On the Measure of Intelligence

Francois Chollet - ARC reflections - NeurIPS 2024

MLST #78 - Prof. NOAM CHOMSKY (Special Edition)

Understanding Deep Learning - Prof. SIMON PRINCE [STAFF FAVOURITE]

#65 Prof. PEDRO DOMINGOS [Unplugged]

MULTI AGENT LEARNING - LANCELOT DA COSTA

Dr. Paul Lessard - Categorical/Structured Deep Learning

Topics covered

Popular Clips

Episode Highlights

Abstraction and Semantics

Neural Networks and ComputationPaul Lessard explores the limitations of current neural networks and their potential future advancements. He discusses the need for novel architectures and theories to enhance neural networks' reasoning and generalization capabilities.

Neural Networks and Computation

Category Theory InsightsDr. Paul Lessard discusses the role of category theory in enhancing the interpretability and composability of neural networks. He highlights its potential to provide a robust conceptual foundation for AI, enabling more effective reasoning and abstraction.

Category Theory Insights

Related Episodes