The Emergence of Knowledge And The Benefits Of Quorum

We propose a model of artificial intelligence (AI) that can reproduce, in principle, an arbitrary distribution of data. Every distinct correlation (or pattern) in the data corresponds, in this model, to a bound state for a set of auxiliary variables. A useful analogy can be made with theories of non-adiabatic transfer of a charged particle in a condensed medium: Distinct patterns correspond to distinct positions of the particle, whose on-site energies are distributed, while the auxiliary variables can be thought of as a polarizable medium. The number of the bound states scales exponentially with the system's size. Thus we connect formation of knowledge with an emergence of a complex free energy landscape, where distinct patterns/memories correspond to distinct free energy minima. Conversely, the Marcus-inverted regime for the environmental degrees of freedom causes such free energy to merge and results in loss of data. We show that there is, in principle, a perfect underlying energy function whose Boltzmann distribution can reproduce an arbitrary distribution of data. In practice, one must use a large number of such energy functions whose performance is comparable. Thus we argue that faithful reproduction of data generally requires sampling of a quorum of free energy minima, thus requiring that the machine operate at finite temperatures. Motion along the landscape requires activation; still, the activation barriers are substantially lowered when the auxiliary degrees of freedom are explicitly used. The present methodology is in contrast with traditional machine-learning platforms, which effectively operate at vanishing temperatures and will generally become kinetically trapped in undesirable configurations. Finally, we propose ways to use simplified machine architectures to mitigate the computational challenges made apparent by the present approach.

Name thesis:degree_name

Doctor of Philosophy

Level thesis:degree_level

Doctoral

Discipline thesis:degree_discipline

Physics

Grantor

University of Houston

Year dc:date.issued

2022

Author dc:creator

• He, Yang

Advisor dc:contributor.advisor

• Lubchenko, Vassiliy

Committee members dc:contributor.committeemember

• Bittner, Eric R.
• Cheung, Margaret S.
• Morrison, Greg

• Artificial intelligence
• Machine learning
• Neural networks
• Data encoding
• Free energy landscape

Statement dc:rights

• The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s).

Language dc:language.iso

eng

Handle dc:identifier.uri

https://hdl.handle.net/10657/13232

OAI identifier oai:identifier

oai:uh-ir.tdl.org:10657/13232