p-Adic Statistical Field Theory and Deep Belief Networks

Abstract

In this work we initiate the study of the correspondence between p-adic statistical field theories (SFTs) and neural networks (NNs). In general quantum field theories over a p-adic spacetime can be formulated in a rigorous way. Nowadays these theories are considered just mathematical toy models for understanding the problems of the true theories. In this work we show these theories are deeply connected with the deep belief networks (DBNs). Hinton et al. constructed DBNs by stacking several restricted Boltzmann machines (RBMs). The purpose of this construction is to obtain a network with a hierarchical structure (a deep learning architecture). An RBM corresponds to a certain spin glass, we argue that a DBN should correspond to an ultrametric spin glass. A model of such a system can be easily constructed by using p-adic numbers. In our approach, a p-adic SFT corresponds to a p-adic continuous DBN, and a discretization of this theory corresponds to a p-adic discrete DBN. We show that these last machines are universal approximators. In the p-adic framework, the correspondence between SFTs and NNs is not fully developed. We point out several open problems.

arXiv commentThe introduction was fully revisited. The condition p>2 was removed

References in corpus (30)

• Machine learning and the physical sciences
• A high-bias, low-variance introduction to Machine Learning for physicists
• p-Adic Mathematical Physics
• p-Adic Models of Ultrametric Diffusion Constrained by Hierarchical Energy Landscapes
• p-Adic description of characteristic relaxation in complex systems
• P-adic numbers and replica symmetry breaking
• Eternal Symmetree
• Restricted Boltzmann Machine, recent advances and mean-field theory
• Statistical mechanics of complex neural systems and high dimensional data
• Neural Networks and Quantum Field Theory
• Replica symmetry breaking related to a general ultrametric space I: replica matrices and functionals
• On $p$-adic Gibbs measures of countable state Potts model on the Cayley tree
• The world as a neural network
• Phase transitions for $P$-adic Potts model on the Cayley tree of order three
• Quantum field-theoretic machine learning
• Nonperturbative renormalization for the neural network-QFT correspondence
• p-Adic open string amplitudes with Chan-Paton factors coupled to a constant B-field
• On $P$-adic Ising-Vannimenus model on an arbitrary order Cayley tree
• p-Adic Path Integrals for Quadratic Actions
• Rigorous quantum field theory functional integrals over the p-adics I: anomalous dimensions
• Non-local non-linear sigma models
• Continuum limits of sparse coupling patterns
• Meromorphic Continuation of Koba-Nielsen String Amplitudes
• p-adic Cellular Neural Networks
• Ultrametric Diffusion, Rugged Energy Landscapes and Transition Networks
• Acausal quantum theory for non-Archimedean scalar fields
• Eigen's Paradox and the Quasispecies Model in a Non-Archimedean Framework
• Self-organized criticality in neural networks
• Graphs, local zeta functions, Log-Coulomb Gases, and phase transitions at finite temperature
• Euclidean Quantum Field Formulation of p-Adic open string amplitudes

Cited by in corpus (3)

• p-Adic Statistical Field Theory and Convolutional Deep Boltzmann Machines
• Emergent quantum mechanics of the event-universe, quantization of events via Denrographic Hologram Theory
• A glimpse into the Ultrametric spectrum