Derives Schwinger-Dyson equations and Ward identities in NN-FT to study anomalies in QFTs via a conserved parameter-space current, yielding a new perspective on symmetries.
Neural network field theories: non-Gaussianity, actions, and locality
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
dataset 1
method 1
citation-polarity summary
fields
hep-th 6representative citing papers
Neural network field theory extended with discrete topological labels recovers the BKT transition and bosonic string T-duality.
α=0 architecture in NNFT minimizes finite-width variance, removes IR corrections, and sets a fundamental SNR bound for correlation functions in scalar field theory.
Simple neural networks trained on crossing symmetry and one anchor point reproduce conformal correlators to within a few percent across many CFTs.
The paper introduces a formalism for constructing conformally invariant defects in Neural Network Field Theories, demonstrates it on two toy scalar models, and provides a neural-network reading of a defect OPE expansion in two-point functions.
The work tests perturbative viability of single-layer neural networks for local QFTs at finite neuron number N in phi^4 theory, finding UV-cutoff-sensitive O(1/N) corrections with weak convergence and proposing a modification for better scaling.
citing papers explorer
-
Anomalies in Neural Network Field Theory
Derives Schwinger-Dyson equations and Ward identities in NN-FT to study anomalies in QFTs via a conserved parameter-space current, yielding a new perspective on symmetries.
-
Topological Effects in Neural Network Field Theory
Neural network field theory extended with discrete topological labels recovers the BKT transition and bosonic string T-duality.
-
Optimal Architecture and Fundamental Bounds in Neural Network Field Theory
α=0 architecture in NNFT minimizes finite-width variance, removes IR corrections, and sets a fundamental SNR bound for correlation functions in scalar field theory.
-
Neural Networks Reveal a Universal Bias in Conformal Correlators
Simple neural networks trained on crossing symmetry and one anchor point reproduce conformal correlators to within a few percent across many CFTs.
-
Conformal Defects in Neural Network Field Theories
The paper introduces a formalism for constructing conformally invariant defects in Neural Network Field Theories, demonstrates it on two toy scalar models, and provides a neural-network reading of a defect OPE expansion in two-point functions.
-
Viability of perturbative expansion for quantum field theories on neurons
The work tests perturbative viability of single-layer neural networks for local QFTs at finite neuron number N in phi^4 theory, finding UV-cutoff-sensitive O(1/N) corrections with weak convergence and proposing a modification for better scaling.