Applied AI Track

Week 1: AI Terminology

• Term definition and AI models outline
• Understanding machine learning, deep learning, and neural networks
• Supervised vs. unsupervised learning
• Introduction to popular AI frameworks and architectures
• Real-world applications of different AI model types

Weeks 2-4: Math for Basic AI Algorithms

• Linear Regression: Understanding relationships in data and making predictions
• Principal Component Analysis (PCA): Dimensionality reduction and feature extraction
• Gaussian Mixture Models: Clustering and probability distributions
• Support Vector Machines: Classification and pattern recognition
• Hands-on exercises with real datasets
• Visualizing mathematical concepts with Python libraries

Weeks 5-6: Coding Models in Python

• Python Coding Basics: Variables, functions, loops, and data structures
• Popular AI libraries from Microsoft: Introduction to Azure ML, ONNX, and other tools
• Working with NumPy, Pandas, and Matplotlib for data science
• AI-Assisted Coding Module: Using GitHub Copilot and other AI coding assistants
• Implementing the algorithms learned in weeks 2-4

Weeks 7-12: AI Portfolio Projects

• Coding Real-World AI Models: Building practical applications from scratch
• Working with real datasets and solving authentic problems
• Training, testing, and evaluating model performance
• Debugging and optimizing your AI models
• Building a Custom Website: Creating a personal portfolio to showcase your models
• Web development basics (HTML, CSS, JavaScript)
• Deploying your models and website to the cloud
• Final project presentation and portfolio review

Example Projects: Image classifier, sentiment analysis tool, recommendation system, predictive model for real-world data, or custom AI-powered web application