Controllable AI: Control Theory meets Artificial Intelligence

Abstract

Control theory is fundamental in the design and understanding of many natural and engineered systems, from cars and robots to power networks and bacterial metabolism. In this talk, we explore how the principles of control and dynamical systems —formalized with control theory— can also play an important role in enhancing Artificial Intelligence (AI). We argue that AI systems are themselves dynamical in nature, and that meaningful dynamics emerge at multiple levels of granularity: from individual computational units that mix information, to full deep layered architectures, and ultimately to the real-world systems in which AI is deployed (such as embodied intelligence). We discuss two specific examples of different levels of granularity where ideas from control and dynamical systems lead to practical advances: first, how analyzing individual information-mixing modules enables improved architecture design grounded in dynamical principles; and second, how applying control-theoretic tools at the level of deep layered architectures allows us to steer and constrain model behavior with formal guarantees. Lastly, we give an overview of how examining AI across these different scales of granularity through a unified control lens reveals new opportunities for principled design, analysis, and control, ultimately moving us toward more efficient, predictable, and controllable AI systems. The aim of this talk is to illustrate the potential of viewing AI through the tools of control and dynamical systems, and to open a discussion about future research directions at the intersection of learning, control, and intelligence.

Bio

Carmen Amo Alonso is a Schmidt Science Fellow affiliated with Stanford University. Her research lies at the intersection of control theory, optimization, and artificial intelligence (AI) with a focus on the principled design of reliable and controllable AI technologies. Carmen’s work seeks to adapt mathematical principles from control theory, traditionally used to ensure safety and predictability in engineered systems, to understand, control, and ultimately improve the behavior of AI systems, including generative models for language applications and embodied systems. At Stanford, Carmen was named an Emerson Consequential Scholar for the potential of her research to positively impact society. Prior to joining Stanford, she was a Fellow at the Artificial Intelligence Center at ETH Zurich. Carmen earned her Ph.D. in Control and Dynamical Systems from Caltech in 2023, where she was advised by Prof. John Doyle. Her thesis was awarded the Milton and Francis Clauser Doctoral Prize, which recognizes the best Ph.D. dissertation of the year across all disciplines at Caltech. During her Ph.D., her research received two IEEE best paper awards, was partially funded by Amazon and D. E. Shaw fellowships, and earned her three Rising Star titles (EECS, Cyber-Physical Systems, and Brain and Cognitive Sciences). Besides her research collaborations across academia and industry, Carmen is committed to education for all. As a member of Clubes de Ciencia, she travels to Mexico in the summer to teach underserved students.