François Chollet's 'On the Measure of Intelligence' challenges the conventional understanding of artificial intelligence by focusing on skill acquisition efficiency rather than mere skill output. The book argues that true intelligence lies in the ability to learn and adapt to new tasks efficiently, using limited data. Chollet introduces the concept of 'generalization' as a key aspect of intelligence, contrasting it with the rote memorization often seen in current AI systems. He proposes the Abstraction and Reasoning Corpus (ARC) challenge as a benchmark for measuring this type of intelligence. The book's central theme is the importance of understanding the underlying processes of learning and adaptation in AI, rather than solely focusing on performance metrics.
In this groundbreaking book, David Deutsch argues that explanations have a fundamental place in the universe and that improving them is the basic regulating principle of all successful human endeavor. The book takes readers on a journey through various fields of science, history of civilization, art, moral values, and the theory of political institutions. Deutsch explains how we form new explanations and drop bad ones, and discusses the conditions under which progress, which he argues is potentially boundless, can and cannot happen. He emphasizes the importance of good explanations, which he defines as those that are 'hard to vary' and have 'reach', and argues that these explanations are central to the Enlightenment way of thinking and to all scientific and philosophical progress.
M. Mitchell Waldrop's book delves into the world of complexity science, exploring how individual elements spontaneously form intricate systems like ecosystems and economies. It highlights the work of luminaries at the Santa Fe Institute, including Nobel laureates Murray Gell-Mann and Kenneth Arrow, and their revolutionary discoveries that could transform multiple scientific disciplines. The book offers a compelling narrative about the scientists behind this emerging field and their quest to understand complex systems.
Alessandro Palmarini is a post-baccalaureate researcher at the Santa Fe Institute working under the supervision of Melanie Mitchell. He completed his undergraduate degree in Artificial Intelligence and Computer Science at the University of Edinburgh. Palmarini's current research focuses on developing AI systems that can efficiently acquire new skills from limited data, inspired by François Chollet's work on measuring intelligence. His work builds upon the DreamCoder program synthesis system, introducing a novel approach called "dream decompiling" to improve library learning in inductive program synthesis. Palmarini is particularly interested in addressing the Abstraction and Reasoning Corpus (ARC) challenge, aiming to create AI systems that can perform abstract reasoning tasks more efficiently than current approaches. His research explores the balance between computational efficiency and data efficiency in AI learning processes.
DO YOU WANT WORK ON ARC with the MindsAI team (current ARC winners)?
MLST is sponsored by Tufa Labs:
Focus: ARC, LLMs, test-time-compute, active inference, system2 reasoning, and more.
Future plans: Expanding to complex environments like Warcraft 2 and Starcraft 2.
Interested? Apply for an ML research position: benjamin@tufa.ai
TOC:
1. Intelligence Measurement in AI Systems
[00:00:00] 1.1 Defining Intelligence in AI Systems
[00:02:00] 1.2 Research at Santa Fe Institute
[00:04:35] 1.3 Impact of Gaming on AI Development
[00:05:10] 1.4 Comparing AI and Human Learning Efficiency
2. Efficient Skill Acquisition in AI
[00:06:40] 2.1 Intelligence as Skill Acquisition Efficiency
[00:08:25] 2.2 Limitations of Current AI Systems in Generalization
[00:09:45] 2.3 Human vs. AI Cognitive Processes
[00:10:40] 2.4 Measuring AI Intelligence: Chollet's ARC Challenge
3. Program Synthesis and ARC Challenge
[00:12:55] 3.1 Philosophical Foundations of Program Synthesis
[00:17:14] 3.2 Introduction to Program Induction and ARC Tasks
[00:18:49] 3.3 DreamCoder: Principles and Techniques
[00:27:55] 3.4 Trade-offs in Program Synthesis Search Strategies
[00:31:52] 3.5 Neural Networks and Bayesian Program Learning
4. Advanced Program Synthesis Techniques
[00:32:30] 4.1 DreamCoder and Dream Decompiling Approach
[00:39:00] 4.2 Beta Distribution and Caching in Program Synthesis
[00:45:10] 4.3 Performance and Limitations of Dream Decompiling
[00:47:45] 4.4 Alessandro's Approach to ARC Challenge
[00:51:12] 4.5 Conclusion and Future Discussions
Refs:
Full reflist on YT VD, Show Notes and MP3 metadata
Show Notes: https://www.dropbox.com/scl/fi/x50201tgqucj5ba2q4typ/Ale.pdf?rlkey=0ubvk7p5gtyx1gpownpdadim8&st=5pniu3nq&dl=0