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/Overfitting.md
+2 -2
View File
@@ -6,7 +6,7 @@ tags: [auto-reinforced, overfitting, machine-learning, model-evaluation, general
last_reinforced: 2026-04-20
---
# [[Overfitting]]
# [[Overfitting|Overfitting]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> "데이터를 외우는 모델의 비극: 훈련용 데이터에만 너무 완벽하게 맞춰진 나머지, 정작 실전(Test data)에서는 작은 변동조차 견디지 못하고 성능이 곤두박질치는 '응용력 제로'의 상태."
@@ -29,6 +29,6 @@ last_reinforced: 2026-04-20
- **정책 변화(RL Update)**: 거대 모델 정책(LLM 등)에서는 파라미터가 압도적으로 많음에도 불구하고 데이터가 워낙 방대하여 과적합보다는 오히려 지식이 부족한 '과소적합(Underfitting)'이나 데이터 바닥남 정책을 걱정하는 시대로 변화함.
## 🔗 지식 연결 (Graph)
- [[L2-Regularization]], [[Noise]], [[Machine Learning (ML)]], Deep Learning (DL), [[Optimization]]
- [[L2-Regularization|L2-Regularization]], [[Noise|Noise]], [[Machine Learning (ML)|Machine Learning (ML)]], Deep Learning (DL), [[Optimization|Optimization]]
- **Modern Tech/Tools**: Dropout, Weight decay, Augmentation, Cross-validation.
---