Thermodynamic AI and the Fluctuation Frontier | Qiskit Seminar Series with Patrick Coles

Abstract:

Many Artificial Intelligence (AI) algorithms are inspired by physics and employ stochastic fluctuations. We connect these physics-inspired AI algorithms by unifying them under a single mathematical framework that we call Thermodynamic AI. Seemingly disparate algorithmic classes can be described by this framework, for example, (1) Generative diffusion models, (2) Bayesian neural networks, (3) Monte Carlo sampling and (4) Simulated annealing. Such Thermodynamic AI algorithms are currently run on digital hardware, ultimately limiting their scalability and overall potential. Stochastic fluctuations naturally occur in physical thermodynamic systems, and such fluctuations can be viewed as a computational resource. Hence, we propose a novel computing paradigm involving Thermodynamic AI hardware, which could accelerate such algorithms. We contrast Thermodynamic AI hardware with quantum computing where noise is a roadblock rather than a resource. Thermodynamic AI hardware can be viewed as a novel form of computing, since it uses a novel fundamental building block. Namely, we identify stochastic units (s-units) as the building blocks of Thermodynamic AI hardware. In addition to these stochastic units, Thermodynamic AI hardware employs a Maxwell's demon device that guides the system to produce non-trivial states. We provide a few simple physical architectures for building these devices and we develop a formalism for programming the hardware via gate sequences.

Bio:

Patrick Coles is the Chief Scientist at Normal Computing. He currently works on Thermodynamic Artificial Intelligence, which is a physics-based hardware paradigm for accelerating probabilistic and generative AI applications. Prior to joining Normal Computing, Patrick led the near-term quantum computing efforts at Los Alamos National Lab (LANL). At LANL, he mapped out the limitations of noisy quantum computers, such as barren plateaus, and investigated the potential of variational quantum algorithms and quantum neural networks. Patrick has a broad background, having done his PhD in solid-state physics at Berkeley and his postdocs in quantum physics, quantum information theory, and quantum cryptography at Carnegie Mellon University, National University of Singapore, and University of Waterloo, respectively. The broad theme of Patrick’s career has been the intersection of physics with computing and information technology.