6 papers
A Coherence Law for Trainability in Noisy Equivariant Quantum Neural Networks
Hassan Ugail, Newton Howard
Symmetry provides a quantum neural network structure, but on its own it does not keep the network trainable once noise is present. We ask which physical quantity decides whether th…
Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach
Hai La Quang, Hassan Ugail, Newton Howard +3
Deep visual recognition models are usually trained and evaluated using metrics such as loss and accuracy. While these measures show whether a model is improving, they reveal very l…
Biharmonic Subdivision on Riemannian Manifolds
Hassan Ugail, Newton Howard
This paper introduces a biharmonic interpolatory subdivision framework on Riemannian manifolds. In the Euclidean setting, the six-point Deslauriers-Dubuc stencil is characterised a…
A Neural Tension Operator for Curve Subdivision across Constant Curvature Geometries
Hassan Ugail, Newton Howard
Interpolatory subdivision schemes generate smooth curves from piecewise-linear control polygons by repeatedly inserting new vertices. Classical schemes rely on a single global tens…
Dynamical Systems Analysis Reveals Functional Regimes in Large Language Models
Hassan Ugail, Newton Howard
Large language models perform text generation through high-dimensional internal dynamics, yet the temporal organisation of these dynamics remains poorly understood. Most interpreta…
Quantifying the Dynamics of Consciousness using Hierarchical Integration, Organised Complexity and Metastability
Hassan Ugail, Newton Howard
Quantifying the neural signatures of consciousness remains a major challenge in neuroscience and AI. Although many theories link consciousness to rich, multiscale, and flexible neu…