publications

2026

1. Metriplector: From Field Theory to Neural Architecture

   Dan Oprisa and Peter Toth

   arXiv preprint, 2026

   Abs arXiv HTML PDF

   YOUR ABSTRACT HERE

2017

1. Criticality & Deep Learning II: Momentum Renormalisation Group

   Dan Oprisa and Peter Toth

   arXiv preprint arXiv:1705.11023, 2017

   Abs arXiv HTML PDF

   Guided by critical systems found in nature we develop a novel mechanism consisting of inhomogeneous polynomial regularisation via which we can induce scale invariance in deep learning systems.

2. Criticality & Deep Learning I: Generally Weighted Nets

   Dan Oprisa and Peter Toth

   arXiv preprint arXiv:1702.08039, 2017

   Abs arXiv HTML PDF

   Motivated by the idea that criticality and universality of phase transitions might play a crucial role in achieving and sustaining learning and intelligent behaviour in biological and artificial networks, we analyse a theoretical and pragmatic experimental set up for critical phenomena in deep learning.

2005

1. Six Gluon Open Superstring Disk Amplitude, Multiple Hypergeometric Series and Euler-Zagier Sums

   Dan Oprisa and Stephan Stieberger

   arXiv preprint hep-th/0509042, 2005

   Abs arXiv HTML PDF

   We compute the six gluon open superstring disk amplitude using multiple hypergeometric series and Euler-Zagier sums.

2003

1. Towards the deconstruction of M-theory

   Ingo Kirsch and Dan Oprisa

   arXiv preprint hep-th/0307180, 2003

   arXiv HTML PDF