bluemsi/2nd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: finalized wiki integrity maintenance (v3.0 standard) - pruned 1400+ stubs and fixed 11k+ ghost links

Browse Source
This commit is contained in:
Antigravity Agent
2026-05-02 09:18:34 +09:00
parent c84dcb8371
commit 6445fcc05b
13150 changed files with 55394 additions and 100862 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics_Blog/Regularization.md
+2 -2
View File
@@ -6,7 +6,7 @@ tags: [auto-reinforced, regularization, overfitting, precision, machine-learning
last_reinforced: 2026-04-20
---
# [[Regularization]]
# [[Regularization|Regularization]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> "복잡함에 대한 벌금: 모델이 훈련 데이터의 사소한 잡음까지 외우려 할 때마다 과감하게 제동을 걸어, 너무 똑똑해 보이기보다 '적당히 단순하고 일반적인' 통찰을 갖게 만들어 실전(Test data) 강자로 키워내는 억제 기술."
@@ -27,6 +27,6 @@ last_reinforced: 2026-04-20
- **정책 변화(RL Update)**: "단순한 것이 최고다(Occam's Razor)"라는 고전 정책을 수학적 수식 정책으로 구현해낸 것이 바로 현대 머신러닝의 정규화 정책임.
## 🔗 지식 연결 (Graph)
- [[Overfitting]], [[L2-Regularization]], [[Noise]], [[Optimization]], [[Machine Learning (ML)]]
- [[Overfitting|Overfitting]], [[L2-Regularization|L2-Regularization]], [[Noise|Noise]], [[Optimization|Optimization]], [[Machine Learning (ML)|Machine Learning (ML)]]
- **Modern Tech/Tools**: Weight decay, Batch Normalization, Dropout layers.
---