Practical Python Artificial Intelligence Programming

Cover Material, Copyright, and License

Preface

1. Book Cover
2. About the Author
3. Using the Example Code
4. Acknowledgements

Python Development Environment

1. Managing Python with uv

Part 1 - Machine Learning

“Classic” Machine Learning

1. Example Material
2. Classification Models using Scikit-learn
3. Classic Machine Learning Wrap-up
4. Optional Practice Problems

Regression and Clustering

1. Regression: Predicting Housing Prices
2. Clustering: Discovering Groups in Data
3. Regression and Clustering Wrap-up
4. Optional Practice Problems

Exploratory Data Analysis and Feature Engineering

1. Exploratory Data Analysis
2. Feature Engineering
3. EDA and Feature Engineering Wrap-up
4. Optional Practice Problems

Anomaly Detection

1. The Wisconsin Breast Cancer Dataset
2. Data Preprocessing
3. Approach 1: Gaussian Statistical Detector
4. Approach 2: Isolation Forest
5. Running the Example
6. Interpreting the Results
7. Anomaly Detection Wrap-up
8. Optional Practice Problems

Part 2 - Deep Learning

The Basics of Deep Learning

1. Using PyTorch for Building a Cancer Prediction Model
2. Optional Practice Problems

Natural Language Processing Using Deep Learning

1. Hugging Face and the Transformers Library
2. Comparing Sentences for Similarity Using Transformer Models
3. Deep Learning Natural Language Processing Wrap-up
4. Optional Practice Problems

Part IV - Overviews of Image Generation, Reinforcement Learning, and Recommendation Systems

Overview of Image Generation

1. Image Generation Using Stable Diffusion and PyTorch
2. Image Generation Using Google’s Imagen API
3. Mini-DALL·E: A Lightweight Alternative
4. Recommended Reading for Image Generation
5. Optional Practice Problems

Categorical Deep Learning: From Axioms to Implementation using Category Theory

1. The Para Category and Lens Composition
2. Markov Categories and Stochastic Morphisms
3. Invariance and Equivariance: Colimits in Geometry
4. The Topos Framework: Subobject Classifiers and Sheaves
5. Natural Transformations and Knowledge Distillation
6. Categorical Deep Learning Wrap-up
7. Optional Practice Problems

Overview of Reinforcement Learning (Optional Material)

1. Overview
2. Available RL Tools
3. An Introduction to Markov Decision Process
4. A Concrete Example: Q-Learning with Gymnasium
5. Reinforcement Learning Wrap-up
6. Optional Practice Problems

Overview of Recommendation Systems (Optional Material)

1. TensorFlow Recommenders
2. Recommendation Systems Wrap-up

Part 3 - Large Language Models

Introduction to Transformers and Large Language Models

1. The Transformer Architecture
2. Tokenization
3. From Transformers to Large Language Models
4. Key Capabilities of Modern LLMs
5. Practical Considerations

LLMs with Public APIs

1. Setup and Authentication
2. Text Generation
3. Thinking Models
4. Multi-Turn Conversations
5. Multimodal Input: Analyzing Images
6. Web Search with LLMs
7. Structured Output
8. Practical Considerations
9. Summary
10. Optional Practice Problems

LLMs with Local Models

1. Installing Ollama
2. Downloading and Running Models
3. Using Ollama from Python
4. Reasoning with Local Models
5. Conversation Memory with Ollama
6. Prompt Caching for Performance
7. Image to Text Description (Vision Models)
8. OpenAI-Compatible API
9. Alternative Tools for Running Local Models
10. Hardware Considerations
11. Summary
12. Optional Practice Problems

Text Adventure Game with an LLM Game Master

1. How It Works
2. The System Prompt
3. The Game Engine
4. Playing the Game
5. Customizing Your Adventure
6. Why This Matters
7. Running the Example
8. Summary

Semantic Web Question Answering with SPARQL and Large Language Models

1. A Live Example to Motivate the Reader
2. What This Program Does
3. The Semantic Web and RDF
4. SPARQL Query Language
5. The Shared Library: library.py
6. Example 1: DBpedia (DBPedia.py)
7. Example 2: Wikidata (Wikidata.py)
8. Example 3: Combined DBpedia + Wikidata (DBPedia_and_Wikidata.py)
9. Running the Code
10. Example Queries
11. Troubleshooting
12. Exercises
13. Further Reading

Part 4 - Symbolic AI and Knowledge Representation

Symbolic AI

1. Comparison of Symbolic AI and Deep Learning
2. Implementing Frame Data Structures in Python
3. Use Predicate Logic by Calling Swi-Prolog
4. Swi-Prolog and Python Deep Learning Interop
5. Soar Cognitive Architecture
6. Constraint Programming with MiniZinc and Python
7. Good Old Fashioned Symbolic AI Wrap-up
8. Optional Practice Problems

Expert Systems Using the Rete Algorithm

1. 1. Rete Engine Architecture & Design
2. 2. Implementing the Trickier Parts of Rete
3. 3. Case Studies & Design Advice
4. Wrap Up
5. Optional Practice Problems

A Chess Engine and AI Player in Pure Python

1. Architecture Overview
2. Board Representation
3. Precomputed Move Tables
4. The Move Class
5. Move Generation
6. Make Move and Unmake Move
7. Zobrist Hashing
8. Evaluation
9. Search: Negamax with Alpha-Beta Pruning
10. The Transposition Table
11. Quiescence Search
12. Move Ordering
13. Iterative Deepening
14. The Interactive CLI
15. Testing with Perft
16. Playing Against the Bot
17. Running the Example
18. Why This Matters
19. Summary

Part 5 - Knowledge Representation

Getting Setup To Use Graph and Relational Databases

1. Querying Wikidata with SPARQL and Python
2. The SQLite Relational Database for Knowledge Representation
3. Optional Practice Problems

Optional Material: A Deeper Dive Into Semantic Web and Linked Data

1. Overview and Theory

Open Knowledge Format (OKF) for Human-Agent Systems

1. References & Inspiration
2. What is Open Knowledge Format (OKF)?
3. Sample Knowledge Bundle Structure
4. Python Architecture: The OKF Explorer
5. Example Output
6. Wrap Up
7. Optional Practice Problems