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/Target-Function-Profiling.md
+2 -2
View File
@@ -6,7 +6,7 @@ tags: [auto-reinforced, optimization, metrics, goal-alignment, profiling, object
last_reinforced: 2026-04-20
---
# [[Target-Function-Profiling]]
# [[Target-Function-Profiling|Target-Function-Profiling]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> "성공의 지점 정의하기: 시스템이 도달해야 할 궁극적인 목표(목적 함수)를 다각도에서 분석하고 세분화하여, 학습과 최적화의 방향이 길을 잃지 않도록 정밀한 나침반을 제작하는 작업."
@@ -30,6 +30,6 @@ last_reinforced: 2026-04-20
- **정책 변화(RL Update)**: AI 모델의 성능 지표 수립 시, 단순히 정확도(Accuracy)라는 타겟을 넘어 공정성(Fairness)과 설명 가능성(Explainability)을 타겟 함수의 필수 프로파일링 항목으로 포함시키는 '다차원 평가지표 수립 정책'이 상설 운영됨.
## 🔗 지식 연결 (Graph)
- [[Sensitivity-Analysis]], [[Operations-Research]], [[Performance Management Systems]], [[Reinforcement Learning (RL)]], [[Ps-Reinforce]]
- [[Sensitivity-Analysis|Sensitivity-Analysis]], [[Operations-Research|Operations-Research]], [[Performance Management Systems|Performance Management Systems]], [[Reinforcement Learning (RL)|Reinforcement Learning (RL)]], [[Ps-Reinforce|Ps-Reinforce]]
- **Modern Tech/Tools**: Profiling toolkits, Objective function visualizers, Python (Optuna, Hyperopt).
---