Emergent complex functionality in microscopic machines and computational models

by Dr. (candidate) Itay Griniasty

Physics department, Cornell University

at Condensed Matter Seminar

Mon, 08 Jan 2024, 11:10
Sacta-Rashi Building for Physics (54), room 207

Abstract

Systems composed of many interacting elements that collaboratively generate a function, such as meta-material robots, proteins, and neural networks are notoriously difficult to design.
Such systems elude traditional explicit design methodologies, which rely on composing individual components with specific subfunctions, such as cogs, springs and shafts, to achieve complex functionality. In part the problem stems from the fact that there are few principled approaches to the design of emergent functionality. In this talk I will describe progress towards creating such paradigms for two canonical systems: I will first describe how bifurcations of the system dynamics can be used as an organizing principle for the design of functionality in protein like machines with magnetic interactions. I will then introduce a computational microscope that we have developed to analyze emergent functionality, and its application to machine learning. There we uncovered compelling evidence that the training of neural networks is inherently low dimensional, suggesting new paradigms for their design.

References
1. T. Yang et al. Bifurcation instructed design of multistate machines. Proceedings of the National Academy of Sciences, 120(34):e2300081120, 2023
2. J. Mao et al. The training process of many deep networks explores the same low-dimensional manifold. arXiv preprint arXiv:2305.01604, 2023.
3. R. Ramesh, et al. A picture of the space of typical learnable tasks. Proc. of International Conference of Machine Learning (ICML), 2023.

Created on 31-12-2023 by Naamneh, Muntaser (mnaamneh)
Updaded on 07-01-2024 by Naamneh, Muntaser (mnaamneh)