Practical TypeScript Artificial Intelligence Programming

Practical TypeScript Artificial Intelligence Programming

Mark Watson
Buy on Leanpub

Table of Contents

Practical TypeScript Artificial Intelligence Programming

  • Cover Material, Copyright, and License
  • Preface
    • About the Author
    • Using the Example Code
    • NPM Security Concerns
    • Acknowledgements
  • Setting Up a TypeScript Development Environment
    • Installing Node.js
    • Installing TypeScript and tsx
    • Creating a New Project
    • Running Existing Projects in directory source-code
    • Running TypeScript Files
    • Environment Variables
    • Code Formatting (Optional)
  • A TypeScript Tutorial for Command-Line AI Programs
    • Type Basics
    • Interfaces and Type Aliases
    • Functions
    • Async/Await and Promises
    • Classes
    • Modules and Imports
    • Error Handling
    • Working with Files
    • Enums and Literal Types
    • Map, Set, and Iterators
    • Practical Patterns for AI Code
    • TypeScript Tutorial Wrap-up
  • Part 1 - Machine Learning
  • “Classic” Machine Learning
    • Example Material
    • Loading CSV Data
    • Classification Using K-Nearest Neighbors
    • Classic Machine Learning Wrap-up
  • Regression and Clustering
    • Regression: Predicting Housing Prices
    • Clustering: Discovering Groups in Data
    • Regression and Clustering Wrap-up
  • Exploratory Data Analysis and Feature Engineering
    • Exploratory Data Analysis
    • Feature Engineering
    • EDA and Feature Engineering Wrap-up
  • Anomaly Detection
    • What Is a Gaussian Distribution?
    • How the Detector Works
    • The Wisconsin Breast Cancer Dataset
    • Project Structure
    • Walking Through the Code
    • Running the Example
    • Using the API in Your Own Code
    • Understanding the Evaluation Metrics
    • Wrap Up
  • Part 2 - Deep Learning
  • The Basics of Deep Learning
    • Using TensorFlow.js for Building a Cancer Prediction Model
  • Natural Language Processing Using Deep Learning
    • Hugging Face and the Transformers.js Library
    • Comparing Sentences for Similarity Using Transformer Models
    • Deep Learning Natural Language Processing Wrap-up
  • Part IV - Overviews of Image Generation, Reinforcement Learning, and Recommendation Systems
  • Overview of Image Generation
    • Image Generation Using the Hugging Face Inference API
    • Image Generation Using Local Ollama Models
    • Recommended Reading for Image Generation
  • Overview of Reinforcement Learning (Optional Material)
    • Overview
    • An Introduction to Markov Decision Process
    • A Concrete Example: Q-Learning
    • Reinforcement Learning Wrap-up
  • Overview of Recommendation Systems (Optional Material)
    • TensorFlow Recommenders
    • Project Structure
    • Item-Based Collaborative Filtering
    • Embedding Matrix Factorization
    • Running the Examples
    • Comparing the Two Approaches
    • Using the API in Your Own Code
    • Recommendation Systems Wrap-up
  • Part 3 - Large Language Models
  • Introduction to Transformers and Large Language Models
    • The Transformer Architecture
    • Tokenization
    • From Transformers to Large Language Models
    • Key Capabilities of Modern LLMs
    • Practical Considerations
  • LLMs with Public APIs
    • Setup and Authentication
    • Text Generation
    • Thinking Models
    • Multi-Turn Conversations
    • Multimodal Input: Analyzing Images
    • Structured Output
    • Tool Use (Function Calling)
    • Practical Considerations
    • Summary
  • LLMs with Local Models
    • Installing Ollama
    • Downloading and Running Models
    • Using Ollama from TypeScript
    • Reasoning with Local Models
    • Conversation Memory with Ollama
    • Describe Content of Images
    • Adding Web Search Tools
    • OpenAI-Compatible API
    • Alternative Tools for Running Local Models
    • Hardware Considerations
    • Summary
  • An AI Command-Line Tool with Search Grounding and Persistent Cache
    • How It Works
    • Prerequisites
    • Project Structure
    • Keyword Extraction
    • The Cache Engine
    • The Main REPL Application
    • Running the Tool
    • Example Session
    • REPL Command Reference
    • Key Takeaways
  • Part 4 - Symbolic AI and Knowledge Representation
  • Classic Graph Search
    • Graphs and Search Representation
    • Implementing Graph Search in TypeScript
    • Example Run
    • Wrap-up
  • Chess Game with Alpha-Beta Search
    • How a Chess Engine Works
    • Project Structure
    • Walking Through the Code
    • Running the Example
    • Wrap Up
  • Part 5 - Knowledge Representation
  • Getting Setup To Use Graph and Relational Databases
    • Querying Wikidata with SPARQL and TypeScript
    • The SQLite Relational Database for Knowledge Representation
  • Optional Material: A Deeper Dive Into Semantic Web and Linked Data
    • Overview and Theory
  • Open Knowledge Format (OKF) Bundle Explorer
    • Inspiration and the Specification
    • The Knowledge Bundle Structure
    • Defining the OKF Data Model
    • Implementing the Knowledge Bundle
    • Building the Consumption Agent
    • Tying It All Together
    • Running the Explorer and Sample Output
    • Summary and Future Improvements
Practical TypeScript Artificial Intelligence Programming/overview

Practical TypeScript Artificial Intelligence Programming

course_overview

count_chapters
begin_reading
download
p_implied_book_part_name

Practical TypeScript Artificial Intelligence Programming28 chapters

Begin ›
  1. Cover Material, Copyright, and License

  2. Preface

  3. Setting Up a TypeScript Development Environment

  4. A TypeScript Tutorial for Command-Line AI Programs

  5. Part 1 - Machine Learning

  6. “Classic” Machine Learning

  7. Regression and Clustering

  8. Exploratory Data Analysis and Feature Engineering

  9. Anomaly Detection

  10. Part 2 - Deep Learning

  11. The Basics of Deep Learning

  12. Natural Language Processing Using Deep Learning

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

  14. Overview of Image Generation

  15. Overview of Reinforcement Learning (Optional Material)

  16. Overview of Recommendation Systems (Optional Material)

  17. Part 3 - Large Language Models

  18. Introduction to Transformers and Large Language Models

  19. LLMs with Public APIs

  20. LLMs with Local Models

  21. An AI Command-Line Tool with Search Grounding and Persistent Cache

  22. Part 4 - Symbolic AI and Knowledge Representation

  23. Classic Graph Search

  24. Chess Game with Alpha-Beta Search

  25. Part 5 - Knowledge Representation

  26. Getting Setup To Use Graph and Relational Databases

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

  28. Open Knowledge Format (OKF) Bundle Explorer