wassname/ml_debug
1
0
Fork 0
mirror of https://github.com/wassname/ml_debug.git synced 2026-06-27 01:00:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs(ml_debug): annotate sanh outbound links with content summaries

Browse Source
This commit is contained in:
wassname
2026-03-10 05:40:31 +08:00
parent c9c53f8e7f
commit 3dffe890b1
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/evidence/sanh_simple_considerations_hf_2021.md
+4 -2
View File
@@ -57,5 +57,7 @@ Credence ~65-70% -- specific domain claim, lacks ablation study reference.
## External links from this post ## External links from this post
- "Checklist for debugging neural networks" -- Cecelia Shao (Towards Data Science) - **Cecelia Shao, "Checklist for Debugging Neural Networks"** (2019, KDnuggets/Towards Data Science): 5-section checklist (start simple, confirm loss, check intermediate outputs, diagnose parameters, track work). Thin; largely overlaps with Karpathy recipe and Slavv. Not captured separately -- see those sources instead.
- "A recipe for Training Neural Networks" -- Karpathy - **Chase Roberts, "How to unit test machine learning code"** (2017, Medium, 4 min): Focuses on software unit testing practices applied to ML models -- testing gradient flow, output shapes, that outputs change when weights change. Spawned `mltest` library. Not a full debugging guide. Main insight: "The code never crashes, the loss still goes down, it just converges to poor results."
- **Joel Grus, "Reproducibility in ML as engineering best practices"** (Google Slides): Experiment reproducibility / engineering hygiene. Not fetched.
- **A recipe for Training Neural Networks** -- Karpathy (captured in full: karpathy_recipe_training_nn_2019.md)