| Home > Publications database > From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning |
| Software | FZJ-2026-01326 |
; ; ; ; ; ; ;
2025
This record in other databases:
Please use a persistent id in citations: doi:10.5281/ZENODO.15480898
Abstract: Code for From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning This repository contains the code accompanying the paper: Rubin, N., Fischer, K., Lindner, J., Dahmen, D., Seroussi, I., Ringel, Z., Krämer, M., Helias, M. From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning (arxiv 2502.03210). For any questions, please contact Noa Rubin (noa.rubin@mail.huji.ac.il), Kirsten Fischer (ki.fischer@fz-juelich.de) or Javed Lindner (javed.lindner@rwth-aachen.de).
Keyword(s): feature learning ; kernel adaptation ; Bayesian inference ; field theory ; deep neural networks ; kernel rescaling
|
The record appears in these collections: |