Course Information
I. Description
This course provides knowledge on artificial intelligence, with a particular focus on machine learning. Learners will gain a solid understanding of core machine learning concepts, including key algorithms for supervised and unsupervised learning, as well as widely-used techniques in the field. The course also guides learners on how to comprehensively set up, implement, and evaluate models, helping them understand the full process of building a machine learning system from start to finish.
II. What You'll learn
-
Grasp the core concepts and mechanics of foundational machine learning algorithms.
-
Develop complete machine learning models using TensorFlow, scikit-learn, and Keras, covering algorithms for regression (like Linear and Lasso Regression) and classification (such as SVM, Naive Bayes, Decision Trees).
-
Master techniques for fine-tuning, evaluating, and optimizing machine learning models to enhance their performance and accuracy.
III. Prerequisites
-
Have a strong foundation in linear algebra, probability, statistics, and basic calculus, enabling you to understand the mathematical concepts behind machine learning.
-
Be comfortable with Python programming, with practical experience in writing and debugging code for machine learning tasks.
-
Have hands-on experience working with popular machine learning libraries, including TensorFlow, Keras, and scikit-learn, to implement and experiment with various algorithms.
IV. Lecture Schedule
| Lecture | Title | Status | Resources |
|---|---|---|---|
| 01 | Introduction to Artificial Intelligence and Machine Learning Basic Concepts | ||
| 02 | Regression Analysis and Regression Algorithm | ||
| 03 | Classification and Logistic Regression Algorithms | ||
| 04 | Data Split, Cross-Validation, Bias-Variance Trade-off, Regularization, Model/Feature Selection and Problems in Machine Learning | ||
| 05 | Naive Bayes Classifier Algorithms | ||
| 06 | Support Vector Machine Algorithms | ||
| 07 | Decision Tree Algorithms | ||
| 08 | Ensemble Method and Random Forest Algorithms | ||
| 09 | Dimensionality Reduction Techniques and Principal Component Analysis Algorithms | ||
| 10 | Unsupervised Learning Techniques, K-Measn Clustering Algorithms and Gaussian Mixture Model |
V. Acknowledgments
I would like to express my heartfelt gratitude to two authors: Andrew Ng, the creator of the CS229 Machine Learning course, and Aurélien Géron, the author of the book Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. Their work has been a tremendous source of inspiration and motivation for me to create these lecture notes.