Artificial Intelligence Hub: Machine Learning, Neural Networks, and Autonomous Systems

Artificial Intelligence (AI) encompasses the theoretical foundations and engineering systems that enable computational agents to perceive environments, extract structured patterns from data, reason under uncertainty, and make autonomous decisions.

This hub organizes classical statistical learning, deep neural network architectures, computer vision, NLP, and agentic workflows.

1. Quick-Reference: AI Sub-Disciplines

+-----------------------------------------------------------------------------------------+
|                               ARTIFICIAL INTELLIGENCE DOMAINS                           |
+-----------------------------------------------------------------------------------------+
| Sub-Discipline         | Mathematical Foundation           | Key Applications           |
+------------------------+-----------------------------------+----------------------------+
| Classical ML           | Convex optimization, statistics   | Gradient boosting, SVMs    |
| Deep Learning          | Backpropagation, tensor compute   | Transformers, ResNets      |
| Generative AI          | Autoregressive attention, diffusion| Code, text, and image synth|
| Reinforcement Learning | Markov Decision Processes (MDP)   | Robotics, game engines     |
| Knowledge Graphs       | Symbolic logic, RDF triple stores | Semantic RAG, reasoning    |
+-----------------------------------------------------------------------------------------+

2. Core Deep Dives

GenerativeAIHub: Large Language Models, RAG, and prompt caching.
ComputerVision: Convolutional networks, vision transformers, and image segmentation.
TopologicalDataAnalysis: Persistent homology and high-dimensional manifold analysis.
MlModelDeploymentHub: Production ML model deployment and serving.

LLM Systems and Agentic Architecture

RetrievalAugmentedGeneration — Dense/lexical hybrid search, Reciprocal Rank Fusion (RRF), and cross-encoder re-ranking.
LangChainFundamentals — LCEL stream execution and LangGraph cyclic state machine orchestration.
TokenBudgeting — Context allocation frameworks, AST pruning, and prompt caching economics.
EfficientContext — Semantic compression, dynamic scratchpads, and context window optimization.
InferenceServing — PagedAttention KV-cache management, continuous batching, and speculative decoding.

Agentic Systems, Knowledge Graphs & Local Inference

InventionOfKnowledgeGraph — Historical evolution from semantic networks and Cyc to modern enterprise RDF graphs.
KnowledgeManagementWithObsidian — Zettelkasten slip-box method, bidirectional linking, and Markdown graph notes.
OllamaSetup — Local LLM quantization, GPU VRAM allocation, and GGUF inference optimization.
OntologyDesignPatterns — Modular OWL ontologies, SKOS taxonomic hierarchies, and reification patterns.
ProductionLocalAI — Private edge inference, vLLM continuous batching, and hardware selection for air-gapped AI.
ResourceDescriptionFrameworkSchema — RDFS subclass hierarchies, property domains, and semantic web inference.
AiContentModerationSystems — Multi-modal toxicity classification, guardrail prompt filtering, and latency SLAs.
AiForDocumentation — Automated AST docstring extraction, change summary generation, and documentation linting.
OpenWebUIToolServer — Function calling servers, WebUI plugin integrations, and secure sandbox execution.
KnowledgeGraphsAndManagement — Unifying enterprise vector stores with structured RDF knowledge graphs.
SupportVectorMachines — Maximal margin hyperplanes, dual Lagrangian formulation, and Mercer kernel tricks.

Specialized Machine Learning Sub-Clusters

[FineTuningLargeLanguageModels Hub](FineTuningLargeLanguageModels Hub) — LoRA, QLoRA, parameter-efficient fine-tuning (PEFT), and dataset curation.
[AnomalyDetectionTechniques Hub](AnomalyDetectionTechniques Hub) — Isolation Forests, autoencoders, and statistical outlier scoring.