Knowledge Base

A comprehensive collection of notes on Artificial Intelligence, Machine Learning, and modern software engineering practices. This knowledge base is designed to serve both as a personal reference and an educational resource for practitioners at all levels.


Where to Start

New to AI and ML? Begin with 01 - AI Fundamentals to understand neural networks, activation functions, and optimization techniques. Then progress to 02 - Machine Learning for classical algorithms.

Interested in Large Language Models? Start with 05 - Generative AI to explore Transformers, prompt engineering, and RAG systems.

Building Production Systems? Head to 07 - MLOps & DevOps for pipelines, deployment strategies, and infrastructure as code.

Looking for Mathematical Foundations? See 08 - Algorithms & Math for linear algebra, probability, and algorithm design.


All Domains

DomainDescription
01 - AI FundamentalsNeural networks, activation functions, loss functions, optimization
02 - Machine LearningSupervised and unsupervised learning, ensemble methods, feature engineering
03 - Deep LearningCNNs, RNNs, LSTMs, autoencoders, GANs
04 - NLPText processing, word embeddings, semantic search
05 - Generative AITransformers, LLMs, prompt engineering, RAG systems
06 - Reinforcement LearningMDPs, Q-learning, policy gradients, RLHF
07 - MLOps & DevOpsML pipelines, model serving, CI/CD, infrastructure as code
08 - Algorithms & MathGraph algorithms, clustering, linear algebra, probability theory

  • Transformers - The architecture powering modern AI systems
  • Attention Mechanisms - Understanding how models focus on relevant information
  • Prompt Engineering - Techniques for effective interaction with LLMs
  • Activation Functions - The building blocks of neural networks
  • Model Evaluation - Metrics and techniques for assessing model performance

References

For a comprehensive introduction to deep learning and neural networks, see Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.1