Python & AI For Dummies

Höfundar: John C. Shovic; Mary Everett (Útgáfa: 1)
Python & AI For Dummies

Kaup valmöguleikar

Unlock the combined power of Python and AI to supercharge your next technical project and your career Python & AI For Dummies explores the exciting combo of two revolutionary technologies that are reshaping how we work, code, and solve problems. Authors John C. Shovic and Mary Everett draw on their extensive work in computer science, precision agriculture, and artificial intelligence to walk you through the intersection of Python programming and AI applications.

No matter your professional background, learn how to use Python's versatility to unlock AI's transformative power. This guide offers hands-on approaches to implementing AI with Python. It moves from foundational concepts to advanced applications, covering essential Python libraries: TensorFlow, PyTorch, OpenCV, and scikit-learn. It also explores essential AI concepts, like neural networks, machine learning models, and natural language processing.

Python & AI For Dummies is packed with hands-on projects and real-world examples, that explain how to build machine vision systems, create language models, implement reinforcement learning, and develop AI agents. Broken down into manageable, jargon-free lessons, explore topics from theoretical programming fundamentals to cutting-edge AI applications. Inside the book: Grasp fundamental AI concepts including machine learning, neural networks, and deep learning architectures Explore eight essential Python libraries designed specifically for AI development and data manipulation Build practical projects, including machine vision systems, large language models, and AI agents Learn proven techniques for data preprocessing, model training, and avoiding common pitfalls like overfitting Gain insights into emerging technologies including generative AI, transformers, and the Model Context Protocol A can’t-miss resource for programmers interested in expanding their AI skillset, professionals in finance or marketing who want to develop new capabilities, and small business owners ready to streamline their operations, Python & AI For Dummies offers step-by-step guidance, troubleshooting tips, and real-world applications in industries from manufacturing to agriculture.

Nánar um bókina

Útgefandi
Wiley Professional Development (P&T)
ISBN
9781394413478
Print ISBN
9781394413461
Format
ePub
Útgáfa
1
Höfundar
John C. Shovic; Mary Everett
Tungumál
English
Útgefið
2026-06-26
Prent takmörkun á líftíma
100
Prent takmörkun
10
Afritunar takmörkun
2

Kaflar

  • Cover
  • Table of Contents
  • Title Page
  • Copyright
  • Introduction
  • About This Book
  • Foolish Assumptions
  • Icons Used in This Book
  • Beyond the Book
  • Where to Go from Here
  • Part 1: Getting Started with Python and AI
  • Chapter 1: Starting with Python Basics
  • Using Python to Work with AI
  • Setting Up a Python Programming Environment
  • First-Time Python Programming Gotchas
  • Creating a Virtual Environment
  • Breaking Down the VS Code Interface
  • Hello, World!
  • Chapter 2: Defining Fundamental AI Concepts
  • Defining AI
  • How Big Data Gave Rise to Machine Learning
  • Breaking Down Models
  • Evaluating and Improving a Model
  • Getting Started in the AI World
  • Chapter 3: Working with Data
  • Preparing Data for a Machine Learning Model
  • Describing the Data
  • Accessing and Filtering the Data
  • Handling Missing Data
  • Visualizing the Data
  • Trusting the Experts: The Importance of Domain Knowledge
  • Part 2: Fundamental Machine Learning Models
  • Chapter 4: Working with the scikit-learn Library
  • An Overview of scikit-learn
  • Installing scikit-learn
  • Preprocessing Data with scikit-learn
  • Dividing Data into Training, Validation, and Test Sets
  • Classification, Regression, and Clustering, Oh My!
  • Using the scikit-learn Model API
  • Chapter 5: The Plot Thickens: Regression Models
  • Taking a Look at a Classic: The Linear Regression Model
  • Implementing Linear Regression Manually in Python
  • Implementing Linear Regression in scikit-learn
  • Not Forgetting Other Regression Models
  • Chapter 6: Making Decisions with Trees
  • Exploring the Beautiful Flowchart of a Decision Tree
  • Understanding Information Theory
  • Programming a Decision Tree
  • Explaining Important Decision-Tree Parameters
  • Chapter 7: Better Together: Boosting, Bagging, and Random Forests
  • Two Heads Are Better than One: Ensemble Models
  • Bragging about Your Bagging Model
  • Boosting Your Models for Liftoff
  • Random Forest: Your scikit-learn Powerhouse
  • When 100 Percent Accuracy Is 100 Percent Wrong
  • It Works Well, But I Have No Idea Why
  • Part 3: The Neural Network Family
  • Chapter 8: Meeting Your Brain: Neural Network Architectures
  • Examining the Biological Concepts of Neural Networks
  • Exploring the Computer Science Model of Neural Networks
  • Chapter 9: The Not-So-Scary Math That Powers Neural Networks
  • Choosing the Right Activation and Error Functions
  • Creating Meaningful Change with Gradient Descent
  • Demystifying Backpropagation
  • Chapter 10: Training a Neural Network
  • Avoiding Data Pitfalls
  • Validating Models
  • Overfitting and Underfitting
  • Setting Neural Network Parameters and Hyperparameters
  • Creating and Training a Neural Network
  • Chapter 11: Identifying the Neural Network Family
  • Exploring the Neural Network Family Tree
  • Building Basic Feed-Forward Networks
  • Creating Convolutional Neural Networks
  • Running Recurrent Neural Networks
  • Analyzing Autoencoders
  • Attention, Please! Transformer Models
  • Using Multiple Architectures in One Network
  • Part 4: Machine Vision with OpenCV
  • Chapter 12: Introducing Machine Vision
  • Your Personal Vision System
  • Comparing Biological Vision with Camera Vision
  • Exploring Common Use Cases for Machine Vision
  • Considering Machine Vision Data Needs
  • Uncovering Potential Machine Vision Pitfalls
  • “Hello Visual World” with OpenCV
  • Chapter 13: Getting Started with OpenCV
  • Your Image Is in the Matrix
  • Manipulating Pixels
  • Color Spaces and Blurry Faces
  • Reviewing Kernel Operations
  • Finding the Image Gradient
  • Refining with Canny Edge Detection
  • From Image Processing to AI
  • Chapter 14: Classifying Images with Convolutional Neural Networks
  • Exploring the AI Machine Vision Task Hierarchy
  • Architecting a Convolutional Neural Network
  • Training a Vision Classification Model in Keras
  • Chapter 15: Creating an Object Detector
  • Collecting Your Dataset
  • Annotating Data with Free Tools
  • Coding with Google Colab
  • Implementing Your Model in Real Time
  • Part 5: Advanced AI Models
  • Chapter 16: Large and in Charge: LLMs
  • Building the House: Architectures of LLMs
  • Transforming the Attention
  • How LLMs Rocked the World
  • Using an LLM via an API in Python
  • Training Your Own LLM
  • Being Mindful of the Limitations of LLMs
  • Chapter 17: Generating Stuff with AI
  • Identifying the Types of Generative AI
  • Exploring Generative Adversarial Networks
  • Making Sense of Data with Variational Autoencoders
  • Imaging with Diffusion Models
  • Generating Code with Transformer Models
  • Last Words on Generative AI
  • Chapter 18: AI Agents: The Ghosts in Our Machines
  • Separating Agentic AI from Traditional AI
  • Building Simple AI Agents in Python
  • Considering the Limitations of AI Agents
  • Chapter 19: Improving Your Computer with Reinforcement Learning
  • Learning about Learning
  • Getting Feedback: Reinforcement Learning
  • Defining Policy with a Markov Chain
  • Optimizing Policy with Gradients
  • Exploring Reinforcement Learning in Python
  • Chapter 20: Nature Knows Best: Using Evolutionary Algorithms
  • Evolving Your Idea of Computation
  • Optimizing Search with a Genetic Algorithm
  • Parameterizing a Genetic Algorithm
  • Implementing a Genetic Algorithm
  • Wrapping Up Your Evolutionary Computation Journey
  • Part 6: The Part of Tens
  • Chapter 21: Ten Steps for Developing an AI Project
  • Step 1: Learn from the Domain Experts
  • Step 2: Define the Problem Types
  • Step 3: Sort Problems by Feasibility and Impact
  • Step 4: Scope Out the Project
  • Step 5: Collect the Data
  • Step 6: Explore the Data
  • Step 7: Choose Appropriate Model Types
  • Step 8: Choose Your Metrics
  • Step 9: Iterate, Iterate, Iterate
  • Step 10: Make Your Outputs Count
  • Chapter 22: Ten Common AI Mistakes to Avoid
  • Skipping Data Exploration and Quality Checks
  • Using the Wrong Evaluation Metrics
  • Overfitting Your Model to Training Data
  • Ignoring Time-Series Considerations
  • Choosing Complex Models When Simple Models Work
  • Trying Only One Set of Model Hyperparameters
  • Forgetting to Consult with Domain Experts
  • Not Quantifying a Model’s Impact
  • Deploying Models without Monitoring
  • Ignoring Ethical and Bias Considerations
  • Appendix: Setting Up Your Development Environment
  • Installing Python and Package Managers
  • IDEs and Editor Recommendations
  • Index
  • About the Authors
  • Dedication
  • Authors’ Acknowledgments
  • Connect with Dummies
  • End User License Agreement