arXiv (All)
open access
When Bias Meets Trainability: Connecting Theories of Initialization
The statistical properties of deep neural networks (DNNs) at initialization play an important role to comprehend their trainability and the intrinsic architectural biases they possess before data exposure Well established mean field (MF) theories have uncovered that the distribution of parameters of
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Learning-Induced Dynamical Transition in Recurrent Neural Networks#1013886
- Hierarchy as Constraint on Revision Randomness: A Conceptual Account of Why Layered Adaptive Systems Learn When Flat Ones Merely React#708825
- Neural Network Representation Formats — Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.V. (US20250384299A1)#607345
- Explainability from Training with Applications to TCR-Epitope Prediction#1131196
- Quantization-Aware Pre-Training with Constrained Empirical Weight Distribution#1116990
Record · ID 1104851
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive