Week 1
Lesson 1
Intro to AI and Machine Learning
In this day, we will explore the concept of intelligence and its connection to artificial intelligence. We will delve into the basics of AI, its significance in today's world, and its various real-world applications. Additionally, we will distinguish between artificial intelligence, machine learning, and data science, and understand the importance of machine learning as a subset of AI.
Lesson 2
Machine Learning Foundations
We will dive into different types of machine learning algorithms and get acquainted with Code with Mu, a popular code editor. This day also introduces the Python libraries NumPy and Pandas for data manipulation and analysis. We will learn how to work with Pandas DataFrames and start our first machine learning project on predicting favorite music genres.
Lesson 3
Machine Learning Project Music Prediction
Continuing with the music prediction project, we will delve deeper into machine learning concepts. We will discuss the types of problems AI can solve and the differences between supervised and unsupervised learning. The day will also cover various steps involved in a machine learning project.
Lesson 4
Data Handling in Python
This day focuses on handling and processing data using Python. We will explore the ethical considerations of data science and the human aspect of AI. The introduction to NumPy and Pandas will be deepened, and we will also learn about Matplotlib, a Python library for data visualization.
 Week 2
Lesson 5
Data Preparation and Ethics in AI
We will explore the relationship between data and artificial intelligence, emphasizing the importance of data collection and preparation for machine learning. The day will also cover the potential problems and ethical challenges associated with AI data. Additionally, we will highlight the importance of research and problem-solving skills in coding.
Lesson 6
Introduction to Scikit-learn and Machine Learning Libraries
We will get introduced to Scikit-learn, a popular machine learning library in Python, and learn about the nearest neighbor algorithm for classification tasks. This day also marks the start of our second machine learning project, which involves classifying species of iris flowers using a linear regression machine learning model.
Lesson 7
Machine Learning Project and Advanced Concepts
We will continue working on the iris classification project and explore decision trees as a method for classification. The day will also cover the concept of loss and how to measure the accuracy of a model. Additionally, we will learn about the importance of splitting data into training and test sets for model evaluation.
Lesson 8
Advanced Machine Learning Projects and Career Paths
In the final day, we will work on a project to classify images as dogs or cats using machine learning algorithms. We will learn how to use Scikit-learn for image classification tasks and revisit the concepts of accuracy in this context. The day will also discuss the importance of test and training data in evaluating image classification models and explore career opportunities in the field of machine learning and artificial intelligence.