p-adic statistical field theory and deep belief networks
There is an investigation on the correspondence between Neural Networks (NN) and Statistical Field Theory (STF). After a short review of important achievements supporting the idea of the existence of a correspondence between different forms of the neural network architectures and quantum field theories, one starts with the presentation of basic aspects of the p-adic analysis. One defines the field of \(p\)-adic numbers, \(\mathbb{Q}_p\), its topology and the Bruhat-Schwartz space. The third section of the article is devoted to the introduction of a class of non-Archimedean statistical field theories. One defines the energy-functional \(E (v, h)\) which controls the size of thermal fluctuations performed by the field \(\{v,h\}\), its discretized form, the standard restricted Boltzmann machines (RBM) and the \(p\)-adic discrete deep belief networks (DBN). In the fourth section one proves that the \(p\)-adic DBNs are universal approximators. A discussion on obtained results and open problems is to be found in the fifth section, followed by Conclusions in the last section. References contain an impressive list of one hundred titles.
- p-adic description of characteristic relaxation in complex systems
- p-adic models of ultrametric diffusion constrained by hierarchical energy landscapes
- p-adic ^ 4-theory as a functional equation problem
- \(p\)-adic open string amplitudes with Chan-Paton factors coupled to a constant \(B\)-field
- \(p\)-adic path integrals for quadratic actions
- p-adic renormalization group solutions and the Euclidean renormalization group conjectures
- A survey on deep learning and its applications
- Acausal quantum theory for non-Archimedean scalar fields
- An introduction to the theory of local zeta functions from scratch
- Beyond mean field theory: statistical field theory for neural networks
- Construction of p-adic covariant quantum fields in the framework of white noise analysis
- Continuum limit in the fermionic hierarchical model
- Critical properties of ^4-theories
- Eigen's paradox and the quasispecies model in a non-Archimedean framework
- Emergent quantumness in neural networks
- Euclidean quantum field formulation of \(p\)-adic open string amplitudes
- Fourier Analysis on Local Fields. (MN-15)
- Giorgio Parisi: the Nobel Prize in Physics 2021
- Graphs, local zeta functions, log-Coulomb gases, and phase transitions at finite temperature
- scientific article; zbMATH DE number 3854171 (Why is no real title available?)
- scientific article; zbMATH DE number 4208857 (Why is no real title available?)
- scientific article; zbMATH DE number 3721546 (Why is no real title available?)
- scientific article; zbMATH DE number 8016 (Why is no real title available?)
- scientific article; zbMATH DE number 53251 (Why is no real title available?)
- scientific article; zbMATH DE number 3566956 (Why is no real title available?)
- scientific article; zbMATH DE number 1199695 (Why is no real title available?)
- scientific article; zbMATH DE number 1273988 (Why is no real title available?)
- scientific article; zbMATH DE number 2146322 (Why is no real title available?)
- scientific article; zbMATH DE number 4117569 (Why is no real title available?)
- scientific article; zbMATH DE number 782642 (Why is no real title available?)
- Information dynamics in cognitive, psychological, social and anomalous phenomena.
- Information, Physics, and Computation
- INTERACTION MEASURES ON THE SPACE OF DISTRIBUTIONS OVER THE FIELD OF p-ADIC NUMBERS
- Learning of p-adic neural networks.
- Meromorphic continuation of Koba-Nielsen string amplitudes
- Non-Archimedean Coulomb gases
- Non-Archimedean statistical field theory
- Non-Archimedean strings and Bruhat-Tits trees
- Non-Archimedean white noise, pseudodifferential stochastic equations, and massive Euclidean fields
- Non-local non-linear sigma models
- Number theory as the ultimate physical theory
- On \(p\)-adic and adelic generalization of quantum field theory
- On \(p\)-adic mathematical physics
- On \(p\)-adic string amplitudes in the limit \(p\) approaches to one
- Onp-adic Gibbs measures of the countable state Potts model on the Cayley tree
- Onp-adic Ising–Vannimenus model on an arbitrary order Cayley tree
- P-ADIC DYNAMICAL SYSTEMS AND NEURAL NETWORKS
- Path integral methods for stochastic differential equations
- Phase transitions for \(p\)-adic Potts model on the Cayley tree of order three
- Probabilistic pathway representation of cognitive information
- Pseudo-differential equations and stochastics over non-Archimedean fields
- Pseudodifferential equations over non-Archimedean spaces
- Reducing the Dimensionality of Data with Neural Networks
- Regularization of p-adic string amplitudes, and multivariate local zeta functions
- Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
- Statistical field theory for neural networks
- Statistical mechanics of complex neural systems and high dimensional data
- Statistical mechanics of learning
- Systematic Fluctuation Expansion for Neural Network Activity Equations
- The \(P(\phi )_{2}\) Euclidean (quantum) field theory.
- The non-Archimedean stochastic heat equation driven by Gaussian noise
- The Principles of Deep Learning Theory
- Theory of p-adic distributions. Linear and nonlinear models
- Tutorial on Neural Field Theory
- Ultrametric diffusion, rugged energy landscapes and transition networks
- Ultrametric Pseudodifferential Equations and Applications
- Understanding recurrent neural networks using nonequilibrium response theory
- P-ADIC DYNAMICAL SYSTEMS AND NEURAL NETWORKS
- p-Adic statistical field theory and convolutional deep Boltzmann machines
- p-Adic Statistical Field Theory and Deep Belief Networks
- The p-adic Schrödinger equation and the two-slit experiment in quantum mechanics
- Quantum mechanics on a \(p\)-adic Hilbert space: foundations and prospects
- Hierarchical neural networks, p-adic PDEs, and applications to image processing
- 2-adic quantum mechanics, continuous-time quantum walks, and the space discreteness
- Dynamic mean-field theory for continuous random networks
- Deep neural networks: a formulation via non-Archimedean analysis
This page was built for publication: \(p\)-adic statistical field theory and deep belief networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2685103)
