Publications

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

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

Transactions on Machine Learning Research (TMLR). Published October, 2026.

Realistic coupling enables flexible macroscopic traveling waves in the mouse cortex

Guanhua Sun*, James Hazelden*, Ruby Kim, and Daniel Forger, * Equal contribution.

eLife, 14:RP108208. Published September, 2026.

Biologically Interpretable Machine Learning Approaches for Analyzing Neural Data

Madelyn Esther Chua Cruz, James Hazelden, Michael I. Ivanitskiy, Matthew D'Alessandro, David Casey Negelspach, Alisa Huskey, William D. S. Killgore, George A. Mashour, Daniel B. Forger

Communications AI & Computing, Accepted for Publication, October, 2026.

Disentangling Computation in Multi-Task Neural Networks with the Green's Operator

James Hazelden

Accepted poster at NeurReps 2026 (NeurIPS workshop); arXiv:2609.40292.

Center-Manifold Reduction of Learning at Bifurcations: Interference and Rich Learning in Recurrent Neural Networks

James Hazelden and Eric Shea-Brown

Accepted poster at NeurReps 2026 (NeurIPS workshop); arXiv:2605.12763.

Hodgkin-Huxley Backpropogation

James Hazelden, Michael Ivanitskiy, and Daniel Forger

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

Preprints

Fast Generalized Neural Tangent Kernel Statistics via Trace Estimation

James Hazelden

Submitted to ICLR 2027; 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.

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.

Back to homepage