Week 1
Lesson 1
Introduction to AI and Machine Learning
Students will explore the concepts of intelligence and AI, discovering how AI is integrated into our daily lives. They'll learn the distinction between AI, Machine Learning, and Data Science, and get hands-on experience with Google Colab, a powerful tool for coding and analysis.
Lesson 2
Fundamentals of Machine Learning and Python
This session introduces different types of Machine Learning and dives into essential Python libraries like NumPy and Pandas. Students will begin their first ML project, predicting favorite music, which will give them a practical understanding of ML applications.
Lesson 3
Machine Learning Concepts and Data Visualization
Students will complete their first ML project and explore the problems AI can solve. They'll learn about supervised and unsupervised learning, key ML terminology, and the overall ML process. The day concludes with an introduction to data visualization using Matplotlib.
Lesson 4
Working with Data and Python
This day focuses on handling data in Python. Students will work with Pandas DataFrames and synthetic data, preparing them for their second ML project comparing height and weight data.
Lesson 5
Introduction to Scikit-learn and Linear Regression
Students will finish their height vs. weight comparison project and delve into the crucial role of data in AI. The class will introduce Scikit-learn, a powerful ML library in Python.  
 Week 2
Lesson 6
Machine Learning and Linear Regression
Students will work on a prediction project using linear regression to predict study hours and grades deepening their understanding of supervised learning algorithms.
Lesson 7
Nearest Neighbors and Model Evaluation
Students will learn about the Nearest Neighbors algorithm and various distance measurements used in ML. They'll also discover the importance of splitting data into test and training sets and how to evaluate model performance using confusion matrices.
Lesson 8
Working with Real-world Datasets
This session introduces the famous Iris dataset and teaches students how to evaluate datasets. They'll apply their knowledge to a Nearest Neighbors project and learn about loss functions and determining model accuracy.
Lesson 9
Neural Networks and Handwriting Classification
Students will begin an exciting project on handwriting classification using neural networks. They'll learn about the history of neural networks, understand concepts like weights and nodes, and review requirements for their final project.
Lesson 10
Completing Neural Networks Project and Final Review
The final day will be dedicated to completing the neural networks handwriting classification project. Students will further explore loss functions and accuracy determination. The course will conclude with a review of key concepts and final project work.