This repository is a structured knowledge base for Computer Science, focusing on Artificial Intelligence, Machine Learning, and Robotics.
The vault is organized into two primary pillars:
- 1. Courses/: High-level Knowledge Maps and curricula. These files act as entry points to specific fields, organizing atomic topics into logical modules and learning sessions.
- 2. Topics/: Atomic, specialized notes categorized by subfield. This is the Lexicology of the vault, containing definitions, mathematical foundations, and technical explanations.
- 3. Images/: A central repository for all visual assets and diagrams referenced across the notes.
These "Hub" files provide a guided path through the topics:
- Computer Programming: Data structures (Arrays, Linked Lists, Hash Tables) and fundamental algorithms (BFS, DFS, Dijkstra, Sorting).
- Computer Vision: From image formation and camera models to modern Deep Learning techniques like Vision Transformers (ViT) and Object Detection.
- Machine Learning: Foundational architectures (Transformers, Self-Attention) and generative models (GANs, Diffusion Models).
- Natural Language Processing: Text analysis pipeline, linguistic foundations, and state-of-the-art Large Language Models (LLMs).
- Reinforcement Learning: Comprehensive coverage from Markov Decision Processes and Bandits to Policy Gradients and Multi-Agent RL.
- Statistical Learning and Prediction: Mathematical foundations of classification, regression, and neural network training.
The lexicology is divided into the following specialized areas:
- AI Reasoning: Evolutionary computation, agents, and heuristic search.
- Calculus: Mathematical foundations for optimization and modeling.
- Computer Architecture: Hardware fundamentals and memory systems.
- Computer Programming: Implementation details of algorithms and data structures.
- Computer Vision: Image processing, geometry, and visual recognition.
- High Performance Computing: Systems-level optimization and parallel processing.
- Machine Learning Foundations: Core neural network concepts and training methodologies.
- Matrices And Linear Transformations: The linear algebra backbone of AI.
- Natural Language Processing: Computational linguistics and text modeling.
- Personality And Emotions: Cognitive modeling and affective computing.
- Probability For Computing: Probabilistic models and statistical inference.
- Reinforcement Learning: Decision-making under uncertainty and agent-environment interaction.
- Software Development: Methodologies and engineering tradeoffs.
- Statistical Learning and Prediction: Theoretical machine learning and predictive modeling.