Machine Learning Essentials with Python (TTML5506-P)

Learn how Artificial Intelligence is being applied in modern business.
This foundation-level hands-on course explores core skills and concepts in machine learning practices. You’ll learn machine learning concepts and algorithms from scratch. This includes the foundations, applicability and limitations, and an exploration of implementation and use.

Course Agenda:

Python for Data Science Quick Refresher

• Review and application of Python basics.
• Relevance of Python in Data Science.
• Exploring Python data science libraries: Pandas, NumPy, Matplotlib.
• Introduction to Jupyter Notebook, Anaconda.
• Lab: Solving basic data science problems using Python.

Introduction to AI and Machine Learning

• Understanding the foundations and significance of AI and Machine Learning.
• Differentiating between AI, Machine Learning, and Deep Learning.
• Overview of the business applications of AI and Machine Learning.
• Exploring types of Machine Learning: Supervised, Unsupervised, Reinforcement.
• Deep dive into common Machine Learning algorithms.
• Introduction to TensorFlow and PyTorch.
• Lab: Exploring Python libraries for Machine Learning.

Supervised Learning: Regression and Classification

• Understanding Simple Linear, Multiple Regression, and Binary Classification.
• Understanding the business context in Binary Classification.
• Lab: Conducting Regression Analysis and Classification using Python.

Unsupervised Learning: Introduction to Clustering

• Understanding the concept of Clustering in Unsupervised Learning.
• Diving deep into k-means clustering algorithm.
• Lab: Implementing k-means Clustering

Data Wrangling and Preprocessing Techniques

• Understanding the importance of data wrangling and preprocessing in Machine Learning.
• Techniques for handling missing data, outliers, and categorical data.
• Feature scaling and normalization techniques.
• Lab: Applying data preprocessing techniques on a dataset.

Practical Machine Learning Project Walkthrough

• Gaining insights into the lifecycle of AI projects in the industry.
• Common challenges in implementing AI projects and solutions
• Step-by-step walkthrough of a real-life AI project from end-to-end.
• Lab: Implementing a small-scale machine learning project.

Model Evaluation and Validation

• Understanding model assessment metrics for both Regression and Classification.
• Learning to split data for model training and testing.
• Lab: Evaluating model performance on test data.

Introduction to Ensemble Learning

• Learning the concept of Ensemble Learning and its importance.
• Understanding simple methods for Ensemble Learning.
• Lab: Implementing simple Ensemble Learning techniques.

Explainable AI and Ethical Considerations in AI.

• Understanding the importance of interpretability in Machine Learning.
• Exploring techniques for making AI transparent.
• Discussing ethical considerations in AI and ML.
• Lab: Visualizing Feature Importance in a model

Introduction to Neural Networks

• Grasping the basics of Neural Networks.
• Learning about Feedforward and Backpropagation processes.
• Lab: Building a basic Neural Network with Python.

Data Visualization Techniques with Python

• Understanding the importance of data visualization in Machine Learning.
• Exploring Python libraries for data visualization: Matplotlib, Seaborn.
• Lab: Visualizing datasets using various plots.

Machine Learning Pipeline and Model Deployment

• Understanding the concept of ML pipeline: Data collection, Preprocessing, Modeling, Evaluation, Deployment.
• Lab: Creating a simple Machine Learning pipeline

Bonus Chapters / Time Permitting (or Day Four)
Bonus Chapter: Exploring Generative AI with GPT-4

• Understand Generative AI and how it powers GPT-4, using Python for interacting with these models.
• Learn about the evolution of GPT models, and the specific advancements of GPT-4 in handling complex Python programming tasks.
• Understand the potential applications of GPT-4 and how to implement them using Python.
• Discuss the ethical considerations and Python coding practices for using powerful models like GPT-4 responsibly.
• Lab: Creating a conversational bot using GPT-4 with Python.

Bonus Chapter: Basics of Integrating AI into Applications

• Understand the concept of AI integration into simple applications.
• Learn about the role of APIs in leveraging AI capabilities in applications.
• Explore how Python can be used to connect applications to AI functionalities.