p-Adic statistical field theory and convolutional deep Boltzmann machines

DOI10.1093/PTEP/PTAD061MaRDI QIDQ6115474zbMATH OpenFDO

Authors

Publication date 12 July 2023

Published in PTEP. Progress of Theoretical and Experimental Physics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2302.03817

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Trees (05C05) Neural nets and related approaches to inference from stochastic processes (62M45) Boltzmann equations (35Q20) Model quantum field theories (81T10) Turing machines and related notions (03D10)

Abstract: Understanding how deep learning architectures work is a central scientific problem. Recently, a correspondence between neural networks (NNs) and Euclidean quantum field theories (QFTs) has been proposed. This work investigates this correspondence in the framework of p-adic statistical field theories (SFTs) and neural networks (NNs). In this case, the fields are real-valued functions defined on an infinite regular rooted tree with valence p, a fixed prime number. This infinite tree provides the topology for a continuous deep Boltzmann machine (DBM), which is identified with a statistical field theory (SFT) on this infinite tree. In the p-adic framework, there is a natural method to discretize SFTs. Each discrete SFT corresponds to a Boltzmann machine (BM) with a tree-like topology. This method allows us to recover the standard DBMs and gives new convolutional DBMs. The new networks use O(N) parameters while the classical ones use O(N^{2}) parameters.

Recommendations

• \(p\)-adic statistical field theory and deep belief networks
• Unified field theoretical approach to deep and recurrent neuronal networks
• The Modern Mathematics of Deep Learning
• P-ADIC DYNAMICAL SYSTEMS AND NEURAL NETWORKS
• Deep learning the Ising model near criticality

Cited in

(4)

• The \(p\)-adic Schrödinger equation and the two-slit experiment in quantum mechanics
• Hierarchical neural networks, \(p\)-adic PDEs, and applications to image processing
• Pseudodifferential equations with regular singularity for radial functions of the \(p\)-adic argument
• Unified field theoretical approach to deep and recurrent neuronal networks

This page was built for publication: p-Adic statistical field theory and convolutional deep Boltzmann machines

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6115474)