A two-volume textbook for checking what is inside AI with your own hands. Volume 1: search, regression, and classification. Volume 2: neural networks, Transformers, and generative AI. Every chapter follows four steps — by hand, build it, visualize, library — with the math explained where it is needed. All code runs on the free tier of Google Colab, with a notebook for each chapter.
Foundations of AI Algorithms Vol.1
Chapter 1 AI and Algorithms
Chapter 2 Search Algorithms
Chapter 3 Linear Regression
Chapter 4 Error and Gradient Descent
Chapter 5 Logistic Regression
Chapter 6 Naive Bayes
Chapter 7 k-Nearest Neighbors (k-NN)
Chapter 8 Decision Trees
Chapter 9 Random Forests and Ensemble Learning
Chapter 10 Support Vector Machines
Chapter 11 Model Evaluation and Generalization
Appendix A Using Google Colab
Appendix B Python, NumPy, pandas, matplotlib, scikit-learn Quick Reference
Appendix C Index of Mathematics by Chapter (Volume 1)
Appendix D Datasets Used (Volume 1)
Foundations of AI Algorithms Vol.2
Chapter 1 k-means Clustering
Chapter 2 Principal Component Analysis (PCA)
Chapter 3 Reinforcement Learning
Chapter 4 Neural Networks
Chapter 5 Backpropagation
Chapter 6 CNN — Learning from Images
Chapter 7 RNN and LSTM — Learning from Sequences
Chapter 8 Attention and the Transformer
Chapter 9 LLMs and Generative AI
Appendix A Google Colab and GPUs
Appendix B PyTorch Quick Reference
Appendix C Index of Mathematics by Chapter (Both Volumes)
Appendix D Datasets Used (Both Volumes)
