James Hazelden — Papers

A crawlable list of papers and preprints, with links to dedicated paper pages.

State-Space NTK Collapse Near Bifurcations

James Hazelden and Eric Shea-Brown

arXiv preprint arXiv:2605.12763, 2026.

The Global Empirical NTK: Self-Referential Bias and Dimensionality of Gradient Descent Learning

James Hazelden, Laura Driscoll, Eli Shlizerman, and Eric Shea-Brown

arXiv preprint arXiv:2605.08746, 2026.

Fast Neural Tangent Kernel Alignment, Norm and Effective Rank via Trace Estimation

James Hazelden

arXiv preprint arXiv:2511.10796, 2025.

KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks

James Hazelden, Laura Driscoll, Eli Shlizerman, and Eric Shea-Brown

arXiv preprint arXiv:2507.06381, 2025.

Whole-cortex simulation reveals spatiotemporal patterns emerging from the interplay of network connectivity and intracellular dynamics

Guanhua Sun, James Hazelden, Ruby Kim, and Daniel Forger

bioRxiv, 2024.01.10.574958, 2024.

Evolutionary algorithms as an alternative to backpropagation for supervised training of biophysical neural networks and neural ODEs

James Hazelden, Yuhan Liu, Eli Shlizerman, and Eric Shea-Brown

arXiv preprint arXiv:2311.10869, 2023.

Hodgkin-Huxley Backpropogation

James Hazelden, Michael Ivanitskiy, and Daniel Forger

NeurIPS 2020 Workshop on Beyond Backpropagation: Novel Ideas for Training Neural Architectures, 2020.

Back to homepage