Application of AI

Application of AI#

Welcome to the Application of AI course materials. This course focuses on practical applications of Artificial Intelligence, with emphasis on Computer Vision and AI Agents.

Course Philosophy#

This course takes a hands-on, application-focused approach to AI. Rather than diving deep into mathematical theory, we prioritize:

  • Practical implementation with industry-standard tools

  • Real-world use cases across multiple domains

  • Progressive skill building from fundamentals to advanced applications

  • Active learning through exercises and experimentation

Students are encouraged to run the code, experiment with parameters, and adapt the examples to their own projects.

Technology Stack#

The course uses Python as the primary programming language, along with:

  • Pillow & OpenCV - Image processing and computer vision fundamentals

  • TensorFlow/Keras - Deep learning and CNN architectures

  • Ultralytics YOLO - State-of-the-art object detection, segmentation, and tracking

  • Python standard library - Framework-free agent concepts and patterns

Prerequisites#

  • Python 3.8+ with Jupyter Notebook or JupyterLab

  • Basic understanding of machine learning concepts (regression, classification, metrics)

  • Familiarity with neural networks (helpful but not required)

  • Interest in practical AI applications

Course Structure#

Part 1: Computer Vision Applications#

This part covers the complete journey from basic image processing to advanced computer vision tasks:

  1. Foundations - Understanding images as data, color spaces, and file formats

  2. Image Processing - Practical tools with Pillow and OpenCV

  3. Deep Learning - CNN architectures and transfer learning with Keras

  4. Advanced CV - Object detection, segmentation, pose estimation, and tracking with Ultralytics YOLO

Part 2: AI Agents#

This part introduces the conceptual foundations of AI agents (framework-free):

  1. LLMs & Prompting - Understanding LLMs, prompt engineering patterns, and effective communication

  2. Agent Architectures - Reactive, deliberative, and hybrid agent designs

  3. Tools & Memory - How agents use external tools and maintain context

  4. CV + Agents - Using computer vision models as perception tools in agent systems

Getting Started#

How to Run These Notebooks#

You have several options for working with the course materials:

Option 1: Google Colab (Easiest)

  • Click the notebook you want in the sidebar, then use the rocket icon (🚀) at the top to launch in Colab

  • No local setup required; runs in your browser with free GPU access

  • Images load directly from the GitHub repository

Option 2: Local Environment

  • Clone the repository: git clone https://github.com/ezponda/ai-application-course-materials.git

  • Install dependencies: pip install -r requirements.txt

  • Launch Jupyter: jupyter notebook or jupyter lab

Option 3: Download Individual Notebooks

  • Use the download button (⬇️) at the top of any notebook page to get the .ipynb file

  • Upload to your preferred environment (Colab, local Jupyter, etc.)

Learning Path#

  1. Work through the notebooks in order (sidebar navigation)

  2. Complete the TODO exercises to reinforce learning

  3. Experiment with your own images and use cases

Each notebook is self-contained with explanations, code examples, and exercises. Notebooks marked with ✅ are complete, while (Placeholder) notebooks contain outlines for upcoming content.

Course materials developed for Master’s level “Application of AI” program.

Contents