Published Dec 20, 2022

#91 - HATTIE ZHOU - Teaching Algorithmic Reasoning via In-context Learning #NeurIPS

Discover how Hattie Zhou's pioneering algorithmic prompting technique redefines AI's approach to complex problem-solving, enhancing the reasoning capabilities of large language models and transforming mathematical theorem proving.

Episode Highlights

Topics covered

Popular Clips

Episode Highlights

Related Episodes

#50 Christian Szegedy - Formal Reasoning, Program Synthesis
Answers 383 questions
#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
Answers 383 questions
Mahault Albarracin - Cognitive Science
Answers 383 questions
#114 - Secrets of Deep Reinforcement Learning (Minqi Jiang)
Answers 383 questions
#73 - YASAMAN RAZEGHI & Prof. SAMEER SINGH - NLP benchmarks
Answers 383 questions
#57 - Prof. Melanie Mitchell - Why AI is harder than we think
Answers 383 questions
#92 - SARA HOOKER - Fairness, Interpretability, Language Models
Answers 383 questions
Jürgen Schmidhuber - Neural and Non-Neural AI, Reasoning, Transformers, and LSTMs
Answers 383 questions
Prof. Subbarao Kambhampati - LLMs don't reason, they memorize (ICML2024 2/13)
Answers 383 questions
#94 - ALAN CHAN - AI Alignment and Governance #NEURIPS
Answers 383 questions
Francois Chollet - ARC reflections - NeurIPS 2024
Answers 383 questions
ICLR 2020: Yoshua Bengio and the Nature of Consciousness
Answers 383 questions
#65 Prof. PEDRO DOMINGOS [Unplugged]
Answers 383 questions
How Do AI Models Actually Think? - Laura Ruis
Answers 383 questions
#045 Microsoft's Platform for Reinforcement Learning (Bonsai)
Answers 383 questions

Dexa/Machine Learning Street Talk (MLST)

#91 - HATTIE ZHOU - Teaching Algorithmic Reasoning via In-context Learning #NeurIPS

Topics covered

Popular Clips

Algorithmic Prompting Technique

Abstract Soft Algorithms

Algorithmic Reasoning Emergence

Computational Limits Speculation

Mathematics in AI

Algorithmic Reasoning Evolution

Episode Highlights

Mathematics in AI

Algorithmic Reasoning

Prompting Techniques

Related Episodes

#50 Christian Szegedy - Formal Reasoning, Program Synthesis

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

Mahault Albarracin - Cognitive Science

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

#73 - YASAMAN RAZEGHI & Prof. SAMEER SINGH - NLP benchmarks

#57 - Prof. Melanie Mitchell - Why AI is harder than we think

#92 - SARA HOOKER - Fairness, Interpretability, Language Models

Jürgen Schmidhuber - Neural and Non-Neural AI, Reasoning, Transformers, and LSTMs

Prof. Subbarao Kambhampati - LLMs don't reason, they memorize (ICML2024 2/13)

#94 - ALAN CHAN - AI Alignment and Governance #NEURIPS

Francois Chollet - ARC reflections - NeurIPS 2024

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

#65 Prof. PEDRO DOMINGOS [Unplugged]

How Do AI Models Actually Think? - Laura Ruis

#045 Microsoft's Platform for Reinforcement Learning (Bonsai)

#91 - HATTIE ZHOU - Teaching Algorithmic Reasoning via In-context Learning #NeurIPS

Topics covered

Popular Clips

Episode Highlights

Mathematics in AIExploring the realm of soft algorithms, Hattie Zhou highlights their potential in AI for solving complex tasks without explicit programming. She also delves into AI's transformative role in mathematics, particularly in theorem proving and conjecturing.

Mathematics in AI

Algorithmic ReasoningHattie Zhou, a PhD student at Université de Montréal and Mila, explores the teaching of algorithmic reasoning to large language models. Her innovative approach, algorithmic prompting, significantly reduces errors and enhances the models' reasoning capabilities.

Algorithmic Reasoning

Prompting Techniques

Related Episodes