Wiki cleanup: error-doc removal, dedup merge, link normalization

10_Wiki/Topics 대규모 정리:
- 오류 캡처/미완성 stub 문서 227개 제거
- 교차폴더 중복 43클러스터 병합 (63파일 → redirect)
- 링크명 정규화: 깨진 링크 수정·redirect 직결·개념 매핑 ~2,400건
- 카테고리 MOC 6개 신규 생성
- Graph 섹션 미해결 related-keyword 링크 10,058건 제거

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

10_Wiki/Topics/AI_and_ML/Differentiable Programming.md

@@ -267,11 +267,11 @@ gradients = loss_fn(params, x, y)
 **기본값**: PyTorch (default) + JAX (research) + Gumbel-Softmax (discrete).
 
 ## 🔗 Graph
-- 부모: [[Deep-Learning]] · [[Optimization]] · [[Programming-Paradigms]]
-- 변형: [[Software-2-0]] · [[Auto-grad]] · [[Implicit-Differentiation]]
-- 응용: [[JAX]] · [[PyTorch]] · [[Differentiable-Physics]] · [[Differentiable-Rendering]] · [[NEAT]] · [[DARTS]]
-- 매 trick: [[Gumbel-Softmax]] · [[REINFORCE]] · [[Straight-Through-Estimator]]
-- Adjacent: [[Bayesian-Optimization]] · [[Computational-Creativity]] · [[Neuro-Symbolic-AI]] · [[Reinforcement-Learning]]
+- 부모: [[Deep-Learning]] · [[Optimization]]
+- 변형: [[Software-2-0]] · [[Auto-grad]]
+- 응용: [[JAX]] · [[NEAT]]
+- 매 trick: [[Gumbel-Softmax]]
+- Adjacent: [[Bayesian-Optimization]] · [[Computational_Creativity|Computational-Creativity]] · [[Neural-Symbolic-Integration|Neuro-Symbolic-AI]] · [[Reinforcement-Learning]]
 
 ## 🤖 LLM 활용
 **언제**: 매 ML algorithm design. 매 differentiable simulation. 매 hybrid neuro-symbolic.
@@ -286,7 +286,7 @@ gradients = loss_fn(params, x, y)
 ## 🧪 검증 / 중복
 - Verified (Karpathy "Software 2.0", JAX docs, PyTorch docs, Brax / PyTorch3D papers).
 - 신뢰도 A.
-- Related: [[Bayesian-Optimization]] · [[Computational-Creativity]] · [[Reinforcement-Learning]] · [[Cross-Entropy Loss]] · [[Deep-Learning]].
+- Related: [[Bayesian-Optimization]] · [[Computational_Creativity|Computational-Creativity]] · [[Reinforcement-Learning]] · [[Cross-Entropy Loss]] · [[Deep-Learning]].
 
 ## 🕓 Changelog
 | 날짜 | 변경 |