Conference Presentation (After Call)

FZJ-2025-03318

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Field Theory of Residual Networks: Residual scaling leads to optimal signal propagation

Fischer, K. (Corresponding author)FZJ* ; Dahmen, D.FZJ* ; Helias, M.FZJ*

2025

---

Contributing Institute(s):

1. Computational and Systems Neuroscience (IAS-6)

Research Program(s):

1. 5232 - Computational Principles (POF4-523) (POF4-523)
2. 5234 - Emerging NC Architectures (POF4-523) (POF4-523)
3. MSNN - Theory of multi-scale neuronal networks (HGF-SMHB-2014-2018) (HGF-SMHB-2014-2018)
4. RenormalizedFlows - Transparent Deep Learning with Renormalized Flows (BMBF-01IS19077A) (BMBF-01IS19077A)
5. ACA - Advanced Computing Architectures (SO-092) (SO-092)
6. neuroIC002 - Recurrence and stochasticity for neuro-inspired computation (EXS-SF-neuroIC002) (EXS-SF-neuroIC002)

Appears in the scientific report 2025

---