fix(topics): 지식 그래프 정상화 — 고아 29%→4%, 인덱스 12개·개념 문서 13편

링크 그래프 분석(6,372문서·31,623링크) 기반 최소 수정 정상화:
- [수정] Topic_CPP/Topic_C 인덱스의 링크 표기를 실제 문서 제목으로 교정
  (CPP 117건·C 68건 — [[CPP Intro]] → [[C++ Intro]] 등, 인덱스 파일 2개만 수정)
- [수정] C Tutorial 별칭에 'C' 추가 — [[c]] 60건 해소 (frontmatter 1줄)
- [신규] 고아 다발 폴더 11곳에 00_INDEX MOC 자동 생성 (Poetic_Blog_Writing 500편,
  AI_and_ML 330, Coding 200, Reasoning_Creativity 161, Frontend 146 등)
- [신규] 루트 MOC(Topics Root Index) — breadcrumb [[10_Wiki/Topics]] 47건을 별칭으로 수용
- [신규] 수요 최상위 미싱 개념 문서 13편 (깨진 링크 다발 해소):
  글쓰기 7편(리듬·감정·문체·블로그·퇴고·정서·구조) + 설계 6편(React·Software
  Architecture·ADR·CQRS·Observability·RLHF) — AI 생성 초안임을 review_reason에 명시
- 기존 문서 본문은 무수정 (인덱스 2개 링크 교정 + 별칭 1줄이 수정의 전부)

결과: 고아 1,901(29%)→314(4%), 완전고립 1,018→173, 깨진 링크 10,258→9,679

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

10_Wiki/Topics/Domain_Programming/AI_and_ML/00_INDEX.md

@@ -0,0 +1,754 @@
+---
+id: ai-and-ml-index
+title: "AI and ML Index"
+category: "Index"
+status: "draft"
+verification_status: "conceptual"
+canonical_id: ""
+aliases: ["AI and ML MOC", "AI and ML 목차"]
+duplicate_of: ""
+source_trust_level: "B"
+confidence_score: 0.90
+created_at: 2026-07-11
+updated_at: 2026-07-11
+review_reason: "고아 문서 연결용 자동 생성 MOC — 폴더 구성 변경 시 재생성 필요"
+merge_history: []
+tags: ["moc", "index"]
+raw_sources: []
+applied_in: []
+github_commit: ""
+---
+
+# [[AI and ML Index]]
+
+## 🎯 한 줄 통찰 (One-line insight)
+`Domain_Programming/AI_and_ML` 폴더의 전체 문서를 연결하는 Map of Content — 이 폴더의 지식으로 들어가는 관문.
+
+## 📚 문서 목록 (728편)
+- [['ADR-0001: Project Chronicle as Independent Module']]
+- [[2014 Combat Controls Update (War Commander)]]
+- [[2026 AI Visual Language Generation Paradigm Shift]]
+- [[20k Skinned Instances Demo (Three.js)]]
+- [[3D Gaussian Splatting (3DGS)]]
+- [[ABA (Applied Behavior Analysis)]]
+- [[Abstract Syntax Tree (AST)]]
+- [[Academic Integrity]]
+- [[ACI (Agent-Computer Interface)]]
+- [[Activism]]
+- [[Actor-Critic Models]]
+- [[Ad-hoc Hypotheses]]
+- [[Adaptive Compute (적응형 계산량 조절)]]
+- [[Addiction Neuroscience]]
+- [[AdSense Revenue Blog Architecture]]
+- [[agargaro Open Source Libraries (Three.js Extensions)]]
+- [[AI & Data Sovereignty]]
+- [[AI Accountability]]
+- [[AI and Narrative]]
+- [[AI Answer Engine Optimization (AEO)]]
+- [[AI Code Assurance (AI 생성 코드 검증)]]
+- [[AI Code Review]]
+- [[AI Code Review + DevSecOps]]
+- [[AI Connect LLM Tool (ConnectAI)]]
+- [[AI Content Production Pipeline]]
+- [[AI Evaluation & Benchmarks]]
+- [[AI Exploitation (Game AI 공략)]]
+- [[AI for Social Good (AI4SG)]]
+- [[AI Generated Code Assurance (AI 생성 코드 검증)]]
+- [[AI Governance Policy (AI Usage Policy)]]
+- [[AI Humanism]]
+- [[AI Image Generation]]
+- [[AI Image Generation & Editing Workflow]]
+- [[AI Image Generation Workflow (canonical)]]
+- [[AI Image Quality Optimization & Debugging]]
+- [[AI Literacy]]
+- [[AI Overviews and SGE (Search Generative Experience)]]
+- [[AI Post-editing Tools (사후 편집)]]
+- [[AI Pursuit Logic (AI 추적 논리)]]
+- [[AI Safety and Alignment]]
+- [[AI Search Optimization]]
+- [[AI 코드 리뷰]]
+- [[AI-Powered Code Analysis (Autofix + Triage)]]
+- [[AI-Powered Code Analysis Tools]]
+- [[AI_and_ML 폴더 시스템 메타]]
+- [[Algorithmic Biology]]
+- [[Algorithmic Fairness]]
+- [[Algorithmic Transparency]]
+- [[Amdahl's Law]]
+- [[Anaemic Domain Model]]
+- [[Anarchism]]
+- [[Anarcho-Primitivism]]
+- [[Anthropic Principle]]
+- [[Anthropomorphism]]
+- [[Antifragility]]
+- [[API Response & State Modeling]]
+- [[API Response Modeling + State Machine]]
+- [[API-backed Image Generation Workflow]]
+- [[Arc 2 — March 2026 Research Drop (War Commander)]]
+- [[Architecture Anti-patterns]]
+- [[Articulateness]]
+- [[Artifacts & Infrastructure (Agentic Systems)]]
+- [[Artificial Intelligence (AI)]]
+- [[Artificial Life (ALife)]]
+- [[Arts (Human + AI Era)]]
+- [[ASD Intervention (AI-Assisted)]]
+- [[Assessment (Educational + ML Evaluation)]]
+- [[Asset-Specific Knowledge]]
+- [[ASTRA 자기 아키텍처]]
+- [[Atmospheric Intelligence (Ambient AI)]]
+- [[Authenticity]]
+- [[Auto-Encoding]]
+- [[Automated Mapping (SLAM / HD Map)]]
+- [[Automated Theorem Proving (ATP)]]
+- [[Autonomous Polling & Wait Automation]]
+- [[Autonomous Vehicles]]
+- [[Availability and Persistence]]
+- [[Awards (Recognition Systems)]]
+- [[Awareness Gap (인지 공백)]]
+- [[Axify (Engineering Productivity Platform)]]
+- [[Axioms]]
+- [[Bag of Words (BoW)]]
+- [[Baiting (Game AI Tactic)]]
+- [[Baseline (Web Platform Features)]]
+- [[Batch Inference]]
+- [[Bayesian Brain Hypothesis]]
+- [[Bayesian Statistics]]
+- [[BCG 2026 Global Gaming Survey]]
+- [[Be Detailed (Specificity Principle)]]
+- [[Beliefs]]
+- [[Benchmarks (AI Evaluation)]]
+- [[BERT (Bidirectional Encoder Representations from Transformers)]]
+- [[Best-of-N Sampling]]
+- [[Bias Correction Algorithm]]
+- [[Bias vs Variance Trade-off]]
+- [[Bibliometrics]]
+- [[Binary Author Identification]]
+- [[Binary Search]]
+- [[Bioenergetics]]
+- [[Biological Intelligence]]
+- [[BioShock (2007) — Game AI & Environmental Narrative]]
+- [[Black-Box Optimization]]
+- [[Blockchain]]
+- [[Blog Production Standard Manual]]
+- [[Bloom Filters]]
+- [[Boltzmann Machines]]
+- [[Boosting Algorithms (XGBoost / LightGBM / CatBoost)]]
+- [[Boss Orchestration & Gimmick Management]]
+- [[Bottlenecks (Performance & Process)]]
+- [[Bounded Contexts (DDD)]]
+- [[Bounded Rationality]]
+- [[Bounding Box Regression]]
+- [[Brain-Computer Interface (BCI)]]
+- [[Brain-Derived Neurotrophic Factor (BDNF)]]
+- [[Brand Consistency in AI Image Generation]]
+- [[C4 Model (Architecture Documentation)]]
+- [[CAP Theorem & PACELC]]
+- [[Case Interviews (Consulting)]]
+- [[Case Study: Allbirds PWA Redesign]]
+- [[Catastrophic Forgetting & Continual Learning]]
+- [[Causal Inference]]
+- [[CFG Scale]]
+- [[CFG Scale (Classifier-Free Guidance)]]
+- [[ChatGPT / Image AI Emoticon Prompt Engineering]]
+- [[ChatGPT Integration (DALL-E + LLM Pipeline)]]
+- [[ChatGPT 통합 기반 텍스트 투 이미지 (Text-to-Image)]]
+- [[Chrome DevTools]]
+- [[Chrome DevTools Memory Profiling]]
+- [[Chronic Pain Management Protocols]]
+- [[CI/CD Pipeline & IDE Security Integration]]
+- [[Circuit Discovery (Mechanistic Interpretability)]]
+- [[Clean Code Principles]]
+- [[Client-Server Architecture Pattern]]
+- [[CLIP (Contrastive Language-Image Pre-training)]]
+- [[Code Smells]]
+- [[Codebase Maps and Interactive Tours]]
+- [[Codebase Onboarding Guide]]
+- [[CodeScene (Behavioral Code Analysis)]]
+- [[Cognition · Overcoming · Action (인지 · 극복 · 행동)]]
+- [[Cognitive Architecture]]
+- [[Cognitive Biases]]
+- [[Cognitive Computing]]
+- [[Cognitive Constraints (Conway's Law & Cognitive Load)]]
+- [[Cognitive Evaluation Theory (Self-Determination)]]
+- [[Cognitive Reserve Theory]]
+- [[Cognitive Therapy in CBT]]
+- [[Cognitive Training Software (Aim Lab, KovaaK's)]]
+- [[Collaborative Filtering]]
+- [[Collaborative Programming (Pair & Mob)]]
+- [[Collective Intelligence]]
+- [[Combat Controls Update (War Commander, Feb 2014)]]
+- [[Combat System & Bullet Interaction Pipeline]]
+- [[Combined Arms (제병협동) 전술]]
+- [[Commercial AI Art Production]]
+- [[CompCert (Verified C Compiler)]]
+- [[Computational Creativity]]
+- [[Computational Linguistics]]
+- [[Computational Neuroscience & Reinforcement Learning]]
+- [[Compute Shader (WebGPU)]]
+- [[Computer Vision]]
+- [[Computer Vision Synthesis (Synthetic Data)]]
+- [[Concept Drift]]
+- [[Connect AI Architecture]]
+- [[Connect AI Documentation]]
+- [[ConnectAI Core Optimization Plan]]
+- [[ConnectAI Dev Log 20260429]]
+- [[Constraint Satisfaction Problems (CSP)]]
+- [[Core Web Vitals]]
+- [[Core Web Vitals Metrics]]
+- [[Core Web Vitals Optimization (INP, LCP, CLS)]]
+- [[Corgea (AI-Native SAST)]]
+- [[Corporate LMS Training]]
+- [[Cost-Benefit Analysis in AI]]
+- [[CPTED (Crime Prevention Through Environmental Design)]]
+- [[Credit Assignment Problem]]
+- [[Critical Rendering Path (CRP)]]
+- [[Cross-Entropy Loss]]
+- [[CSS Animations & Performance]]
+- [[CSS Container Queries]]
+- [[Custom ESLint Rules Development]]
+- [[Cybernetics Foundations]]
+- [[Damage Types (Game Design)]]
+- [[Data Augmentation Strategies]]
+- [[Data Cleaning Algorithms]]
+- [[Data Distillation]]
+- [[Data Ethics and Privacy]]
+- [[Data Flywheel Effect]]
+- [[Data Pipeline Orchestration]]
+- [[DCGAN (Deep Convolutional GAN)]]
+- [[Debugging Methods]]
+- [[Decision Trees and Random Forests]]
+- [[Deep Grammar]]
+- [[DeepCode AI (Snyk Code)]]
+- [[Deepfake Technology]]
+- [[Default Mode Network (DMN)]]
+- [[Defensive Architecture (Game Design)]]
+- [[Degrees of Freedom (DOF)]]
+- [[Deliberate Practice]]
+- [[Denavit-Hartenberg Parameters]]
+- [[Dependency Injection (DI)]]
+- [[Depth Pre-Pass]]
+- [[Development Communication Standards]]
+- [[DevSecOps]]
+- [[Diagrams as Code]]
+- [[Differentiable Programming]]
+- [[Dimensionality Reduction]]
+- [[Discriminated Unions]]
+- [[Distributed Systems]]
+- [[DOM vs Virtual DOM]]
+- [[Domain-Specific Languages (DSL)]]
+- [[DPO (Direct Preference Optimization)]]
+- [[Drama Management Systems]]
+- [[DRY Principle (Don't Repeat Yourself)]]
+- [[Dynamic Creative Optimization (DCO)]]
+- [[Dynamic Difficulty Adjustment (DDA)]]
+- [[Dynamic Environment Handling]]
+- [[Dynamic Few-Shot Selection]]
+- [[Dynamic Pricing & Offers]]
+- [[E-commerce Optimization]]
+- [[Ecology and Ecosystem Modeling]]
+- [[Economics of Information]]
+- [[Edge AI and Computing]]
+- [[Eligibility Traces]]
+- [[Elite Sport Science Protocols]]
+- [[Embodied AI]]
+- [[Embodied Cognition]]
+- [[Emergence in Complex Systems]]
+- [[Emotional AI (Affective Computing)]]
+- [[Emotionally Intelligent Tutoring Systems (EITS)]]
+- [[Encapsulation and Information Hiding]]
+- [[Encapsulation of Domain Invariants]]
+- [[Ensemble Methods]]
+- [[Enterprise Software Engineering]]
+- [[Epidemiological Modeling]]
+- [[Epistemic Uncertainty]]
+- [[Epistemology]]
+- [[ESLint Static Analysis]]
+- [[Ethics & AI]]
+- [[Eudaimonia and Well-being]]
+- [[Eugen Systems 모딩 매뉴얼]]
+- [[Event Sourcing Pattern]]
+- [[Event-Driven Architecture]]
+- [[Evolutionary Biology]]
+- [[Excessive Agency (LLM)]]
+- [[Execution Environment (Sandbox)]]
+- [[Executive Function Deficit]]
+- [[Exhaustiveness Checking]]
+- [[Experience Replay]]
+- [[Explainable AI (XAI)]]
+- [[Exploding Gradient Problem]]
+- [[Exploratory Data Analysis (EDA)]]
+- [[Expo 2025 Osaka]]
+- [[Exponential Growth]]
+- [[Extended Reality (XR)]]
+- [[Extreme Programming (XP)]]
+- [[Factor Analysis]]
+- [[Factory Pattern]]
+- [[Failable Task Handling]]
+- [[Fate War]]
+- [[Feature Clamping (피처 고정)]]
+- [[Feature Engineering]]
+- [[Figma Integration]]
+- [[Figurative Language]]
+- [[Fine-tuning]]
+- [[Finished Goods (제품 완성품)]]
+- [[Finite Element Analysis (FEA)]]
+- [[Finite State Machines (FSM)]]
+- [[Fitness Landscape]]
+- [[Flash Attention]]
+- [[Flexbox]]
+- [[Focal Loss]]
+- [[Formal Methods]]
+- [[Foundation Models]]
+- [[Frame Type Restoration]]
+- [[Free Energy Principle (FEP)]]
+- [[Fuzzy Logic]]
+- [[G-Stack Principles]]
+- [[Game System Design Prompt]]
+- [[Gaussian Processes (GP)]]
+- [[Generalization in AI]]
+- [[Generative Adversarial Networks (GAN)]]
+- [[Generative AI]]
+- [[Geriatric Medicine]]
+- [[Git Branching Strategies]]
+- [[Global Standard]]
+- [[Goal-Oriented Action Planning (GOAP)]]
+- [[Google Page Experience 2025 Update]]
+- [[GPU]]
+- [[GPU Acceleration (Compositing)]]
+- [[GPU Programming with CUDA]]
+- [[Graph Neural Networks (GNN)]]
+- [[Grit]]
+- [[Grouped-Query Attention (GQA)]]
+- [[Growth Mindset]]
+- [[GRPO (Group Relative Policy Optimization)]]
+- [[Hallucination in LLMs]]
+- [[Heuristics]]
+- [[Hexagonal Architecture]]
+- [[Hidden Markov Model (HMM)]]
+- [[High Availability Systems]]
+- [[Homeostasis (항상성)]]
+- [[Homomorphic Encryption (HE)]]
+- [[Hopfield Network]]
+- [[Human-Centered AI (HCAI)]]
+- [[Human-in-the-Loop (HITL)]]
+- [[Hyperparameters]]
+- [[ICRE Framework]]
+- [[IEEE P3652.1 (Federated ML Standard)]]
+- [[Ikigai (이키가이)]]
+- [[Image Classification]]
+- [[Image Parameters]]
+- [[Image Prompt 작성 방법]]
+- [[Image Segmentation]]
+- [[Imbalanced Data Handling]]
+- [[Independent Component Analysis (ICA)]]
+- [[Inductive Bias]]
+- [[Information Retrieval (IR)]]
+- [[Information Theory]]
+- [[Innovative Problem Solving]]
+- [[InstancedMesh2 library]]
+- [[Integrated Development Environment]]
+- [[Intellectual Property in AI]]
+- [[Intentional Failure Induction]]
+- [[Interaction to Next Paint (INP)]]
+- [[Interdisciplinary Research]]
+- [[Interop 2026]]
+- [[Introduction to Programming]]
+- [[Introspection (자기성찰)]]
+- [[Inverse Kinematics (IK)]]
+- [[IoT and AI Integration]]
+- [[Isaac Asimov's Laws of Robotics]]
+- [[Iterative Prompting]]
+- [[JIT Compilation in AI Engines]]
+- [[JSON-LD Structured Data]]
+- [[Just-in-time Data Loading]]
+- [[K-Means Clustering]]
+- [[K-Nearest Neighbors (k-NN)]]
+- [[Kernel Methods and SVMs]]
+- [[Key-Value (KV) Cache]]
+- [[Knowledge Representation in AI]]
+- [[L1 and L2 Regularization]]
+- [[Label Noise and Robustness]]
+- [[Large Frontend Projects]]
+- [[Latent Dirichlet Allocation]]
+- [[Latent Semantic Analysis (LSA)]]
+- [[Layer Normalization]]
+- [[Layout Thrashing]]
+- [[Lazy Loading Strategies]]
+- [[Leaky ReLU and Activations]]
+- [[Lean Operations]]
+- [[Legacy Modernization]]
+- [[Lifecycle Hooks]]
+- [[Lighting and Composition]]
+- [[Linear Discriminant Analysis]]
+- [[Linear Programming]]
+- [[Linear Regression Mastery]]
+- [[Linguistic Analysis in AI]]
+- [[LLM Ops and Tuning]]
+- [[LLM-as-a-Judge (LaaJ)]]
+- [[LLM-based Code Analysis]]
+- [[Load Balancing Strategies]]
+- [[Local AI and Infrastructure]]
+- [[Local Brain Management]]
+- [[LOD]]
+- [[Logic]]
+- [[Logistic Regression Foundations]]
+- [[Long Animation Frames API]]
+- [[Long Tail]]
+- [[Long Tasks API]]
+- [[Loss Functions Foundations]]
+- [[Machine Zone의 4X 포트폴리오 확장 및 라이브 서비스 모델 고도화]]
+- [[Macros (매크로)]]
+- [[Main Thread]]
+- [[Manhattan Distance]]
+- [[MAP Estimation (Maximum A Posteriori)]]
+- [[Markov Chain Monte Carlo (MCMC)]]
+- [[Markov Chains]]
+- [[Matrix Factorization]]
+- [[Matrix Operations and AI]]
+- [[Mean Absolute Error (MAE)]]
+- [[Mean Squared Error (MSE)]]
+- [[Mechanistic Interpretability (기계적 해석 가능성)]]
+- [[Medical Imaging Data Augmentation]]
+- [[Memory Hierarchy]]
+- [[Mermaid Diagrams as Code]]
+- [[Micro-management (RTS)]]
+- [[Midjourney]]
+- [[Mipmap]]
+- [[Miscellaneous AI Topics]]
+- [[Mixed Platoons (혼합 편대)]]
+- [[Mixture of Experts (MoE) & Sparse Architectures]]
+- [[Mobile AI Optimization]]
+- [[Mobile-First Approach]]
+- [[Model Parameters]]
+- [[Modern Engineering Practices (현대적 엔지니어링 프랙티스)]]
+- [[Modern Scalable Frontend Architecture]]
+- [[Momentum and Optimization]]
+- [[Monetization (BM)]]
+- [[Monopoly GO! 및 Royal Match의 라이브 이벤트 구조]]
+- [[Monte Carlo Methods]]
+- [[Moodboard Creation]]
+- [[Morphological and Syntactic Analysis]]
+- [[Multi-armed Bandit Problem]]
+- [[Multinomial Naive Bayes]]
+- [[Naive Bayes Classifiers]]
+- [[Named Entity Recognition (NER)]]
+- [[Natural Language Generation (NLG)]]
+- [[Natural Language Processing (NLP)]]
+- [[Negative Prompt]]
+- [[Neural Architecture Search (NAS)]]
+- [[Neural Darwinism]]
+- [[Neural Style Transfer]]
+- [[Neural-Symbolic Integration]]
+- [[Neurodevelopmental Disorders]]
+- [[Neuropharmacology of Substance Use Disorders]]
+- [[Neuroprosthetics Development]]
+- [[Neuropsychiatric Disorders]]
+- [[Neurorehabilitation Post-Stroke]]
+- [[NLP Attention Mechanisms]]
+- [[No Man's Sky]]
+- [[Noise Reduction in AI]]
+- [[Non-parametric Models]]
+- [[Normalization]]
+- [[NotebookLM Research Workflow]]
+- [[Object Detection Foundations]]
+- [[Occupational Therapy]]
+- [[Olympic Training Protocols]]
+- [[Omni Reference (--oref)]]
+- [[On-Device AI (Mobile / Gemma)]]
+- [[One-Hot Encoding]]
+- [[Ontology Engineering]]
+- [[Open Source AI Ecosystem]]
+- [[OpenAI API Integration]]
+- [[Operation - Western Sun]]
+- [[Optical Character Recognition]]
+- [[Optimization in AI]]
+- [[Ordinal Data Analysis]]
+- [[Out-of-Distribution Detection]]
+- [[Outlier Detection Techniques]]
+- [[P-Reinforce]]
+- [[P-Reinforce 위키 포맷 정본]]
+- [[Parameter]]
+- [[Parameter Control]]
+- [[Parameter Sharing]]
+- [[Pareto Principle]]
+- [[Pattern Recognition]]
+- [[PEFT (Parameter-Efficient Fine-Tuning)]]
+- [[Perceptrons-Foundations]]
+- [[Philosophy]]
+- [[Physical Intelligence]]
+- [[Physics-informed Neural Networks]]
+- [[Plutchik's Wheel of Emotions]]
+- [[PMI Technique (Pointwise Mutual Information)]]
+- [[Poetic Computation]]
+- [[Point Cloud Processing]]
+- [[Point of Sale]]
+- [[Policy Optimization]]
+- [[POMDP]]
+- [[Pooling]]
+- [[Pose Estimation]]
+- [[Positive Prompt]]
+- [[Positive Reinforcement]]
+- [[Pre-processing Data for AI]]
+- [[Precision-Recall Tradeoff]]
+- [[Predictive Analytics]]
+- [[Predictive Coding]]
+- [[Predictive Maintenance]]
+- [[Prenatal Neurology]]
+- [[Principal Component Analysis]]
+- [[Privacy Preserving AI]]
+- [[Probability and Logic Fusion]]
+- [[Problem Solving Test (PST)]]
+- [[Procedural Narrative Generation]]
+- [[Process Automation with AI]]
+- [[Processing]]
+- [[Productivity Hacks for Devs]]
+- [[Prompt Weight]]
+- [[Proprioception]]
+- [[Pros Cons Table]]
+- [[Pull Request (PR)]]
+- [[PyTorch Foundations]]
+- [[PyTorch Lightning]]
+- [[Quality Gates]]
+- [[Quantum Computing for AI]]
+- [[Real-time Operation]]
+- [[Recommendation Systems]]
+- [[Reconciliation]]
+- [[Refactoring Best Practices]]
+- [[Reference]]
+- [[Refinement]]
+- [[Reflection]]
+- [[Reflow and Repaint]]
+- [[Render Tree]]
+- [[Replenishment]]
+- [[Requirements]]
+- [[Reranking]]
+- [[Research]]
+- [[ResNet Architectures]]
+- [[Reward Prediction Error]]
+- [[Reward Shaping in RL]]
+- [[Ring Attention]]
+- [[Rise of Kingdoms]]
+- [[Risk Assessment with AI]]
+- [[RL Neuroscience]]
+- [[Robotics]]
+- [[Robustness]]
+- [[ROC-AUC Curves]]
+- [[ROUGE Metrics]]
+- [[Rule-based Systems]]
+- [[SaaS (Software as a Service)]]
+- [[Samuel Beckett]]
+- [[SAR (Synthetic Aperture Radar)]]
+- [[SARD 안티치트 솔루션 (SARD Anti-Cheat)]]
+- [[SCA Fundamentals (Software Composition Analysis)]]
+- [[SCADA]]
+- [[Scalability in AI Systems]]
+- [[Scaling Laws for LLMs]]
+- [[Schema]]
+- [[Science of Failure]]
+- [[Scientific Communication]]
+- [[SCM (Supply Chain Management)]]
+- [[Search Methodology]]
+- [[Search Optimization]]
+- [[Secrets Detection]]
+- [[Sector Breach August 2025]]
+- [[Secure Multi-party Computation]]
+- [[Seed]]
+- [[Segments.ai]]
+- [[Selective State Space Models (Mamba)]]
+- [[Self-Driving Car Foundations]]
+- [[Self-Evolving Agent 기법 조사 (2026-06)]]
+- [[Self-Play (자기 대결 기반 강화학습)]]
+- [[Self-Verification]]
+- [[Semantic Grounding & Provenance]]
+- [[Semantic Search]]
+- [[Semgrep Assistant]]
+- [[Sensitivity Analysis]]
+- [[Sentiment Analysis]]
+- [[Separation of Concerns (관심사의 분리)]]
+- [[Sequence Diagram]]
+- [[Sequence to Sequence Models]]
+- [[Serverless Computing for AI]]
+- [[shadcn/ui]]
+- [[Shape Feature Extraction]]
+- [[Similarity Metrics in AI]]
+- [[Simulation Environments]]
+- [[Skybound Asset Generation Roadmap]]
+- [[Skybound Defensive Architecture Reboot]]
+- [[Skybound Firepower Overclock v1.5]]
+- [[Skybound Protocol 코드리뷰]]
+- [[Smart Contract Auditing]]
+- [[SME (Subject Matter Expert / Small-Medium Enterprise)]]
+- [[Snyk Checkmarx Endor Labs 등 종합 애플리케이션 보안 플랫폼]]
+- [[Soft Navigation]]
+- [[Software Architecture Pattern]]
+- [[Software Architecture Styles]]
+- [[Software Composition Analysis (SCA)]]
+- [[Software Maintenance]]
+- [[Solution]]
+- [[SonarQube]]
+- [[Sparse Attention]]
+- [[Sparse Data Handling]]
+- [[Spatial Partitioning]]
+- [[Spectral Clustering]]
+- [[Speech Recognition Foundations]]
+- [[Speech Synthesis]]
+- [[Spiking Neural Networks (SNNs)]]
+- [[Splash Damage]]
+- [[SPOF (Single Point of Failure)]]
+- [[SSQ Questionnaire]]
+- [[Stages of Grief]]
+- [[Staircase Monetization Model]]
+- [[Startup]]
+- [[Startup Projects]]
+- [[State Space]]
+- [[Static Site Generation (SSG)]]
+- [[Stem Analysis]]
+- [[Straightening]]
+- [[Structuralism]]
+- [[Structurizr]]
+- [[Style Reference (--sref)]]
+- [[Style Transfer]]
+- [[StyleCounsel]]
+- [[Styletron]]
+- [[Superficiality Metrics]]
+- [[Supply Chain]]
+- [[Support Insulated]]
+- [[Sustainability]]
+- [[Symbolic AI vs Connectionism]]
+- [[Symbols]]
+- [[Symmetry and Invariance]]
+- [[Synergy]]
+- [[Synthesized Intelligence]]
+- [[Synthetic Data]]
+- [[System Prompt (시스템 프롬프트)]]
+- [[System Theory]]
+- [[Tactical Air Drop and Supply Logistics]]
+- [[Tactical Evolution of the War Commander Combat Ecosystem]]
+- [[Tailwind CSS v4]]
+- [[Team Collaboration]]
+- [[Team Topologies]]
+- [[TensorFlow Foundations]]
+- [[Term Frequency-Inverse Document Frequency]]
+- [[Test Time Compute Scaling (추론 시간 계산 스케일링)]]
+- [[Test-Driven Development]]
+- [[Text Mining]]
+- [[The Evolution of Music Distribution]]
+- [[Theory of Constraints (TOC)]]
+- [[Theory of Mind (ToM) in AI]]
+- [[Threejs WebGPURenderer]]
+- [[Time Series Analysis]]
+- [[Time to Interactive (TTI)]]
+- [[Tokenization & Subword Processing]]
+- [[Tool Usage Optimization]]
+- [[Toxicity and Bias Mitigation]]
+- [[Trustworthy AI]]
+- [[Turing Test]]
+- [[Ubiquitous Language]]
+- [[Ultra Efficiency]]
+- [[Unconscious Structuralism]]
+- [[Unit Stances]]
+- [[Universal Approximation Theorem]]
+- [[Universal Basic Income (UBI)]]
+- [[useDeferredValue]]
+- [[useTransition]]
+- [[V-component (Evaluation Interface)]]
+- [[Vary Region (인페인팅)]]
+- [[Virtual DOM과 Reconciliation]]
+- [[Vocabulary Expansion]]
+- [[Voice Assistant Architecture]]
+- [[War Commander 전투 시스템]]
+- [[Weak Central Coherence]]
+- [[Web3 and AI Integration]]
+- [[WebSplatter (3D Gaussian Splatting)]]
+- [[What is AI]]
+- [[Willingness to Pay (WTP)]]
+- [[Word Representation]]
+- [[Work Displacement (AI 노동 대체)]]
+- [[Workflow Integrity]]
+- [[게이미피케이션]]
+- [[공급망 공격 (Supply Chain Attack)]]
+- [[구역 통제 및 동맹 전쟁 (Sector Control and Alliance Wars)]]
+- [[기지 레이아웃 메타 (Base Layout Meta)]]
+- [[기지 방어 (Base Defense)]]
+- [[다수 팀 협업 환경]]
+- [[단일 코드베이스를 통한 멀티 디바이스(모바일-데스크톱) 웹 인터페이스 구축]]
+- [[데이터 기반 밸런싱 (Data-Driven Balancing)]]
+- [[데이터 중심의 SaaS 어드민 패널 및 CRM 대시보드 구축]]
+- [[덱 빌딩 (Deck building)]]
+- [[렌더링 최적화 개념 설명 자료]]
+- [[렌더링 파이프라인(Rendering Pipeline)]]
+- [[맞춤형 팩 (Personalized Packs)]]
+- [[모델 매개변수 제어 (Model Parameter Control)]]
+- [[모듈식 컴포넌트 (Modular Components)]]
+- [[미드저니 및 스테이블 디퓨전의 부분 편집 기법]]
+- [[미디어 쿼리(Media Queries)]]
+- [[미호요(miHoYo)]]
+- [[반응형 디자인]]
+- [[버전 및 모델 (Versions and Models)]]
+- [[병원 (Hospital)]]
+- [[부정 프롬프트와 가중치를 활용한 시각적 아티팩트(Artifact) 디버깅 및 제어]]
+- [[브라우저 렌더링 프로세스 (CRP)]]
+- [[브라우저 메모리 누수 탐지(Browser Memory Leak Detection)]]
+- [[브라우저 메인 스레드 최적화 및 타임 슬라이싱]]
+- [[사후 편집 (Post-editing)]]
+- [[상성 및 데미지 유형(Unit Counters & Damage Profiles)]]
+- [[상업용 브랜드 이미지 및 디자인 시스템 구축]]
+- [[상업용 제품 사진 및 브랜드 로고 디자인]]
+- [[상태 관리 및 API 응답 모델링 (State Management and API Response Modeling)]]
+- [[상태 관리 최적화 (Zustand Jotai Valtio)]]
+- [[샘플링 스텝 (Sampling Steps)]]
+- [[성능 중심의 웹 애니메이션 및 인터랙션 구현]]
+- [[세계 지도(World Map)]]
+- [[섹터 분쟁 및 전초기지 전투(Sector Warfare and Elite Event Operations)]]
+- [[소셜 미디어 그래픽 및 마케팅 캠페인 제작]]
+- [[소프트웨어 아키텍처 다이어그램 (Software Architecture Diagrams)]]
+- [[숨겨진 스탯 (Hidden Stats)]]
+- [[스타일 코드 (Style Codes)]]
+- [[스테이블 디퓨전 기반 정밀 이미지 합성 및 해부학적 오류 수정 파이프라인]]
+- [[스테이블 디퓨전의 가중치 및 제어 시스템]]
+- [[시리즈물 및 다중 샷 워크플로우 (Series and Multi-shot Workflow)]]
+- [[안구 운동 증상(Oculomotor Symptoms)]]
+- [[애니메이션 (transition / keyframes)]]
+- [[약탈적 수익화 (Predatory Monetization)]]
+- [[에셋 재사용(Asset Reuse)]]
+- [[오픈소스 기반 맞춤형 이미지 생성 워크플로우 구축]]
+- [[오픈소스 이미지 모델 미세 조정 및 배포]]
+- [[오픈소스 컴포넌트 (Open Source Components)]]
+- [[원신(Genshin Impact)]]
+- [[월드 오브 워크래프트(World of Warcraft)]]
+- [[웹 접근성 및 prefers-reduced-motion]]
+- [[웹 접근성 및 성능 최적화]]
+- [[유닛 상성(Unit Counters)]]
+- [[유지보수 가능한 CSS 아키텍처(CSS Modules & Tailwind)]]
+- [[유지보수성(Maintainability)]]
+- [[유틸리티 퍼스트(Utility-first)]]
+- [[이미지 생성 및 제어 파이프라인]]
+- [[이미지 생성 최적화 (Image Generation Optimization)]]
+- [[인-이미지 텍스트(In-Image Text)]]
+- [[인공지능 시각 언어 생성 (AI Visual Language Generation)]]
+- [[일관된 캐릭터 및 스타일 구축]]
+- [[자연어 아티팩트 (Natural Language Artifacts)]]
+- [[자연어 프롬프트(Natural Language Prompt)]]
+- [[전자상거래 소비자 참여 및 보상 시스템 최적화]]
+- [[전자상거래 플랫폼]]
+- [[전투 전술(Battle Strategies)]]
+- [[정적 분석 툴 (ESLint, Prettier)]]
+- [[제로잉 (Getting Zero-ed)]]
+- [[제병협동 (Combined Arms)]]
+- [[조명 및 카메라 사양 지시(Lighting and Camera Specification)]]
+- [[초기 로드 시간 (Initial Load Time)]]
+- [[초상화 및 애니메이션 스타일 제어]]
+- [[초인플레이션(Hyperinflation)]]
+- [[카산드라(Cassandra)]]
+- [[코드 속성 그래프 CPG]]
+- [[코드베이스 읽기 지식]]
+- [[크로스 플랫폼 기술(Cross-Platform Technology)]]
+- [[텍스트 렌더링(Text Rendering)]]
+- [[페이 투 윈 (Pay to Win)]]
+- [[포탑 시스템(Turret Systems)]]
+- [[프론트엔드 기초 구조 이해]]
+- [[프론트엔드 기초 구조 이해 핵심 목적]]
+- [[프롬프트 구문 (Prompt Syntax)]]
+- [[플랫폼 저항성(Platform Resistances)]]
+- [[하이브리드 코드 리뷰]]
+- [[해부학적 오류 디버깅 워크플로우]]
+- [[확장 가능한 스타일 시스템]]

10_Wiki/Topics/Domain_Programming/AI_and_ML/RLHF.md

@@ -0,0 +1,37 @@
+---
+id: rlhf
+title: "RLHF"
+category: "AI"
+status: "draft"
+verification_status: "conceptual"
+canonical_id: ""
+aliases: ["RLHF", "Reinforcement Learning from Human Feedback", "인간 피드백 강화학습"]
+duplicate_of: ""
+source_trust_level: "B"
+confidence_score: 0.80
+created_at: 2026-07-11
+updated_at: 2026-07-11
+review_reason: "깨진 링크 다발 해소용 AI 생성 초안 — 원출처 리서치로 검증·보강 권장"
+merge_history: []
+tags: ["ai","llm","training"]
+raw_sources: []
+applied_in: []
+github_commit: ""
+---
+
+# [[RLHF]]
+
+## 🎯 한 줄 통찰 (One-line insight)
+인간의 선호 판단을 보상 신호로 바꿔 언어 모델을 미세조정하는 기법 — "정답"을 정의하기 어려운 품질(유용함·무해함)을 사람의 비교 선택으로 학습시킨다.
+
+## 🧠 핵심 개념 (Core concepts)
+- **3단계 파이프라인** — ① 지시 데이터로 SFT(지도 미세조정) ② 사람이 응답 쌍을 비교한 데이터로 보상 모델 학습 ③ 보상 모델을 신호로 정책(LLM)을 강화학습(PPO 등) 최적화.
+- **보상 해킹 위험** — 모델이 보상 모델의 허점을 파고들어 점수만 높은 응답을 낸다. KL 페널티로 원 모델에서 과도하게 벗어나지 않게 잡는다.
+- **변형들** — 보상 모델 없이 선호 쌍으로 직접 최적화하는 DPO 등 경량 대안이 실무에서 확산됐다.
+- **아첨(sycophancy) 부작용** — 사람이 "듣기 좋은 답"을 선호하는 경향이 보상에 새어들어 모델이 아부하게 될 수 있다.
+
+## 🧩 추출된 패턴 (Extracted patterns)
+- RLHF 의 품질은 알고리즘보다 선호 데이터의 품질(누가·어떤 기준으로 비교했나)이 결정한다.
+
+## 🔗 Knowledge Connections
+- **Related Topics:** [[Software Architecture]]