Bernhard Schölkopf, Director at the Max Planck Institute for Intelligent Systems, merges insights from physics, biology, and machine learning. He discusses how evolution might favor causal inference over mere correlation and the intricate ties between differential equations and causal models. Schölkopf emphasizes the importance of understanding biological intelligence to enhance AI development. Plus, he shares his exciting new book project, aiming to bridge gaps in causal inference and its application across disciplines.
34:53
forum Ask episode
web_stories AI Snips
view_agenda Chapters
menu_book Books
auto_awesome Transcript
info_circle Episode notes
question_answer ANECDOTE
Thinking as Internal Action
Conrad Lorenz compared thinking to "acting in an imagined space".
This metaphor highlights the importance of internal models for intelligent behavior.
insights INSIGHT
Beyond Statistical Representations
Current AI excels at statistical representation learning, focusing on correlations and patterns.
Shifting towards interventional representations, incorporating actions, is key for true intelligence.
insights INSIGHT
Correlation vs. Causation in Learning
Humans and animals rely heavily on correlational learning, likely for efficiency.
Causal models become crucial in situations requiring deeper understanding and generalization.
Get the Snipd Podcast app to discover more snips from this episode
Vladimir Vapnik's 'Statistical Learning Theory' is a seminal work in machine learning, providing a comprehensive framework for understanding and applying statistical learning methods. The book delves into the theoretical foundations of learning from data, emphasizing the importance of generalization and risk minimization. It explores various learning algorithms, including support vector machines (SVMs), and discusses the trade-offs between model complexity and generalization performance. Vapnik's work has significantly influenced the development of modern machine learning techniques and continues to be a valuable resource for researchers and practitioners alike. The book's rigorous mathematical treatment and insightful analysis have shaped the field's understanding of learning theory.
Chemistry, Quantum Physics and Reductionism
Chemistry, Quantum Physics and Reductionism
null
Hans Primas
Estimation of Dependencies from Empirical Data
Estimation of Dependencies from Empirical Data
null
Vladimir Vapnik
Elements of Causal Inference
Elements of Causal Inference
Jonas Peters
Dominik Janzing
Bernhard Scholkopf
This book provides a comprehensive introduction to causal inference, covering various methods and techniques for causal analysis. It delves into the fundamental concepts of causality, including directed acyclic graphs (DAGs) and causal diagrams. The book also explores advanced topics such as causal discovery, causal effects estimation, and causal mediation analysis. It is a valuable resource for researchers and practitioners in various fields who want to learn about causal inference.
Gödel, Escher, Bach
An Eternal Golden Braid
Douglas Hofstadter
This book by Douglas Hofstadter is a comprehensive and interdisciplinary work that explores the interrelated ideas of Kurt Gödel, M.C. Escher, and Johann Sebastian Bach. It delves into concepts such as self-reference, recursion, and the limits of formal systems, particularly through Gödel's Incompleteness Theorem. The book uses dialogues between fictional characters, including Achilles and the Tortoise, to intuitively present complex ideas before they are formally explained. It covers a wide range of topics including cognitive science, artificial intelligence, number theory, and the philosophy of mind, aiming to understand how consciousness and intelligence emerge from formal systems[2][4][5].
Ficciones
Julio Pagano
Gabriela Aberastury
Jorge Luis Borges
Ficciones es una colección de cuentos que destacan por su complejidad y profundidad filosófica. Publicada entre 1941 y 1956, incluye historias como 'Tlön, Uqbar, Orbis Tertius' y 'La biblioteca de Babel', que han convertido a Borges en un referente literario mundial. Las narrativas de Borges desafían la percepción del tiempo, la realidad y el conocimiento.
Causal AI: The Melting Pot. Can Physics, Math & Biology Help Us?
What is the relationship between physics and causal models?
What can science of non-human animal behavior teach causal AI researchers?
Bernhard Schölkopf's rich background and experience allow him to combine perspectives from computation, physics, mathematics, biology, theory of evolution, psychology and ethology to build a deep understanding of underlying principles that govern complex systems and intelligent behavior.
His pioneering work in causal machine learning has revolutionized the field, providing new insights that enhance our ability to understand causal relationships and mechanisms in both natural and artificial systems.
In the episode we discuss:
Does evolution favor causal inference over correlation-based learning?
Can differential equations help us generalize structural causal models?
What new book is Bernhard working on?
Can ethology inspire causal AI researchers?
Ready to dive in?
About The Guest Bernhard Schölkopf, PhD is a Director at Max Planck Institute for Intelligent Systems. He's one of the cofounders of European Lab for Learning & Intelligent Systems (ELLIS) and a recepient of the ACM Allen Newell Award, BBVA Foundation Frontiers of Knowledge Award, and more. His contributions to modern machine learning are hard to overestimate. He's a an affiliated professor at ETH Zürich, honorary professor at the University of Tübingen and the Technical University Berlin. His pioneering work on causal inference and causal machine learning inspired thousands of researchers and practitioners worldwide.
Causal Bandits Podcast 
