Bert de Vries, a professor at Eindhoven University, shares his expertise on intelligent autonomous agents. He discusses the principle of least action, its universal implications, and how it relates to optimizing energy in systems. Bert delves into active inference's role in ecosystems and engineering, particularly in adaptive technologies like hearing aids. He highlights the importance of probabilistic inference for the future of intelligence and explores challenges of implementing these concepts in real-world applications, emphasizing adaptability and innovation.
02:27:39
forum Ask episode
web_stories AI Snips
view_agenda Chapters
menu_book Books
auto_awesome Transcript
info_circle Episode notes
insights INSIGHT
Active Inference and Least Action
Active inference is rooted in the principle of least action.
This principle from Lagrangian mechanics provides a solid foundation for AI, engineering, and science.
insights INSIGHT
Least Action and Equations of Motion
The principle of least action minimizes energy differences, leading to equations of motion.
These equations describe various phenomena, including information processing in biological systems.
question_answer ANECDOTE
Autonomous Driving Example
Bert de Vries uses an autonomous driving example to explain active inference challenges.
He highlights the need for dynamic resource allocation for Kalman filters tracking multiple objects.
Get the Snipd Podcast app to discover more snips from this episode
This book provides a logical and unified approach to data analysis using Bayesian probability theory. It covers topics from parameter estimation to image processing, including reliability analysis, multivariate optimization, and experimental design. The second edition includes a new chapter on handling outliers and correlated noise, along with contributions on 'nested sampling' for Bayesian computation.
Probability Theory: The Logic of Science
The Logic of Science
E.T. Jaynes
E.T. Jaynes's 'Probability Theory: The Logic of Science' offers a comprehensive and rigorous treatment of probability theory, emphasizing its logical foundations. Jaynes argues that probability is not merely a measure of subjective belief or long-run frequencies, but rather a framework for logical reasoning under conditions of incomplete information. The book presents a coherent and consistent approach to probability, integrating Bayesian methods and emphasizing the importance of prior knowledge in statistical inference. It challenges traditional frequentist interpretations and provides a powerful alternative for scientific modeling and decision-making. Jaynes's work has had a profound impact on various fields, including physics, statistics, and artificial intelligence.
Pattern Recognition and Machine Learning
Christopher M. Bishop
This book offers a detailed introduction to pattern recognition and machine learning, integrating both fields under a common statistical framework. It covers topics such as Bayesian methods, graphical models, kernel-based algorithms, and neural networks, making it suitable for advanced undergraduates, first-year PhD students, researchers, and practitioners. The book includes a wide range of exercises and is supported by additional materials like lecture slides and figures.
Watch behind the scenes with Bert on Patreon: https://www.patreon.com/posts/bert-de-vries-93230722
https://discord.gg/aNPkGUQtc5
https://twitter.com/MLStreetTalk
Note, there is some mild background music on chapter 1 (Least Action), 3 (Friston) and 5 (Variational Methods) - please skip ahead if annoying. It's a tiny fraction of the overall podcast.
YT version: https://youtu.be/2wnJ6E6rQsU
Bert de Vries is Professor in the Signal Processing Systems group at Eindhoven University. His research focuses on the development of intelligent autonomous agents that learn from in-situ interactions with their environment. His research draws inspiration from diverse fields including computational neuroscience, Bayesian machine learning, Active Inference and signal processing.
Bert believes that development of signal processing systems will in the future be largely automated by autonomously operating agents that learn purposeful from situated environmental interactions.
Bert received nis M.Sc. (1986) and Ph.D. (1991) degrees in Electrical Engineering from Eindhoven University of Technology (TU/e) and the University of Florida, respectively. From 1992 to 1999, he worked as a research scientist at Sarnoff Research Center in Princeton (NJ, USA). Since 1999, he has been employed in the hearing aids industry, both in engineering and managerial positions. De Vries was appointed part-time professor in the Signal Processing Systems Group at TU/e in 2012.
Contact:
https://twitter.com/bertdv0
https://www.tue.nl/en/research/researchers/bert-de-vries
https://www.verses.ai/about-us
Panel: Dr. Tim Scarfe / Dr. Keith Duggar
TOC:
[00:00:00] Principle of Least Action
[00:05:10] Patreon Teaser
[00:05:46] On Friston
[00:07:34] Capm Peterson (VERSES)
[00:08:20] Variational Methods
[00:16:13] Dan Mapes (VERSES)
[00:17:12] Engineering with Active Inference
[00:20:23] Jason Fox (VERSES)
[00:20:51] Riddhi Jain Pitliya
[00:21:49] Hearing Aids as Adaptive Agents
[00:33:38] Steven Swanson (VERSES)
[00:35:46] Main Interview Kick Off, Engineering and Active Inference
[00:43:35] Actor / Streaming / Message Passing
[00:56:21] Do Agents Lose Flexibility with Maturity?
[01:00:50] Language Compression
[01:04:37] Marginalisation to Abstraction
[01:12:45] Online Structural Learning
[01:18:40] Efficiency in Active Inference
[01:26:25] SEs become Neuroscientists
[01:35:11] Building an Automated Engineer
[01:38:58] Robustness and Design vs Grow
[01:42:38] RXInfer
[01:51:12] Resistance to Active Inference?
[01:57:39] Diffusion of Responsibility in a System
[02:10:33] Chauvinism in "Understanding"
[02:20:08] On Becoming a Bayesian
Refs:
RXInfer
https://biaslab.github.io/rxinfer-website/
Prof. Ariel Caticha
https://www.albany.edu/physics/faculty/ariel-caticha
Pattern recognition and machine learning (Bishop)
https://www.microsoft.com/en-us/research/uploads/prod/2006/01/Bishop-Pattern-Recognition-and-Machine-Learning-2006.pdf
Data Analysis: A Bayesian Tutorial (Sivia)
https://www.amazon.co.uk/Data-Analysis-Bayesian-Devinderjit-Sivia/dp/0198568320
Probability Theory: The Logic of Science (E. T. Jaynes)
https://www.amazon.co.uk/Probability-Theory-Principles-Elementary-Applications/dp/0521592712/
#activeinference #artificialintelligence
Machine Learning Street Talk (MLST) 
