Events Calendar

CS Colloquium: Paul Bogdan (USC / ECE) - Theoretical Foundations of NeuroAI: Challenges and A Gedanken Modeling Framework Motivated by Living Neuronal Networks Dynamics

Speaker: Paul Bogdan, USC / ECE

Talk Title: Theoretical Foundations of NeuroAI: Challenges and A Gedanken Modeling Framework Motivated by Living Neuronal Networks Dynamics

Abstract: Brains build compact models or discover governing laws of the world from just a few assumptions or noisy and conflicting observations. Biological brains can also predict uncanny events via memory-based analogies even when resources are limited. The ability of biological intelligence to discover, generalize, hierarchically reason and plan, and complete a wide range of unknown heterogeneous tasks calls for a comprehensive understanding of how distributed networks of interactions among neurons, glia, and vascular systems enable animal and human cognition. Such an understanding can serve as a basis for advancing the design of artificial general intelligence (AGI). In this talk, we will discuss the challenges and potential solutions for inferring the theoretical foundations of biological intelligence and NeuroAI which can guide the design of future A(G)I, expanding the limit of human discovery. To infer network structures from very scarce and noisy data, we propose a new mathematical framework capable of learning the emerging causal fractal memory from biological neuronal spiking activity. This framework offers insight into the topological properties of the underlying neuronal networks and helps us predict animal behavior during cognitive tasks. We will also discuss an AI framework for mining the optical imaging of brain activity and reconstructing the weighted multifractal graph generators governing the neuronal networks from very scarce data. This network generator inference framework can reproduce a wide variety of network properties, differentiate varying structures in brain networks and chromosomal interactions, and detect topologically associating domain regions in conformation maps of the human genome. We will discuss how network science-based AI can discover the phase transitions in complex systems and help with designing protein–nanoparticle assemblies. To infer the objectives and rules by which distributed networks of neurons attain intelligent decisions, we discuss an AI framework (multiwavelet-based neural operator) capable of learning, solving, and forecasting sets of coupled governing laws. We thus learn the operator kernel of an unknown partial differential equation (PDE) from noisy scarce data. For time-varying PDEs, this model exhibits 2-10X higher accuracy than state-of-the-art machine learning tools. Inspired by the multifractal formalism for detecting phase transitions in biological neuronal networks, we explore the principles of self-organization in Large Language Models (LLMs). Through the lens of multifractal analysis, we reveal the intricate dynamics of neuron interactions, showing how self-organization facilitates the emergence of complex patterns and intelligence within LLMs.  
 
This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Paul Bogdan is the Jack Munushian Early Career Chair associate professor in the Ming Hsieh Department of Electrical and Computer Engineering at University of Southern California. He received his Ph.D. degree in Electrical & Computer Engineering at Carnegie Mellon University. His work has been recognized with a number of honors and distinctions, including the 2021 DoD Trusted Artificial Intelligence (TAI) Challenge award, the USC Stevens Center 2021 Technology Advancement Award for the first AI framework for SARS-CoV-2 vaccine design, the 2019 Defense Advanced Research Projects Agency (DARPA) Director’s Fellowship award, the 2018 IEEE CEDA Ernest S. Kuh Early Career Award, the 2017 DARPA Young Faculty Award, the 2017 Okawa Foundation Award, the 2015 National Science Foundation (NSF) CAREER award, the 2012 A.G. Jordan Award from Carnegie Mellon University for an outstanding Ph.D. thesis and service, and several best paper awards. His research interests include cyber-physical systems, new computational cognitive neuroscience tools for deciphering biological intelligence, the quantification of the degree of trustworthiness and self-optimization of AI systems, new machine learning techniques for complex multi-modal data, the control of complex time-varying networks, the modeling and analysis of biological systems and swarms, new control techniques for dynamical systems exhibiting multi-fractal characteristics, performance analysis and design methodologies for heterogeneous manycore systems.

Host: CS Department

Location: Olin Hall of Engineering (OHE) - 132

Audiences: Everyone (USC) is invited

Contact: CS Faculty Affairs