arXiv (All)
open access
Flat Loss, Evolving Features: Grokking in Modular Addition
Can a network keep learning while its training cross-entropy stays nearly flat at a positive level? We show that it can. On modular addition, a standard testbed for grokking, ReLU networks trained with supported-Polar hidden updates, normalized output-layer updates and weight decay can keep 100% tra
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
- Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning#176975
- Fixed Points Without Fixed Diffusion: Implicit Neural Sheaves for Convergent Test-Time Computation#1104476
- Unifying network connectivity from geodesics to random walks via the random cluster model.#449879
- Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets#660815
- Aligned Consensus Teaching for Label-Efficient Oriented Object Detection in Weakly-Aligned Visible-Infrared Imagery#1011820
Record · ID 1386566
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