Conformal Defects in Neural Network Field Theories
By: Pietro Capuozzo, Brandon Robinson, Benjamin Suzzoni
Potential Business Impact:
Builds math models that understand special rules.
Neural Network Field Theories (NN-FTs) represent a novel construction of arbitrary field theories, including those of conformal fields, through the specification of the network architecture and prior distribution for the network parameters. In this work, we present a formalism for the construction of conformally invariant defects in these NN-FTs. We demonstrate this new formalism in two toy models of NN scalar field theories. We develop an NN interpretation of an expansion akin to the defect OPE in two-point correlation functions in these models.
Similar Papers
Fermions and Supersymmetry in Neural Network Field Theories
High Energy Physics - Theory
Builds new computer models for physics.
Viability of perturbative expansion for quantum field theories on neurons
High Energy Physics - Theory
Helps computers understand tiny particle rules.
Fermionic neural Gibbs states
Quantum Physics
Models how tiny particles behave when hot.