Nhân bản – Phụng sự – Khai phóng
Introduction to
Machine Learning Course
Machine Learning
Course Description
1. Overview of Machine Learning
2. Machine Learning Project
3. Regression Techniques
4. Classification Techniques
5. Clustering Techniques
6. Ensemble Learning & Random Forests
7. Dimensionality Reduction
No of credits: 3
8. Neural Networks & Deep Learning
Lectures: 2
9. Recommender Systems Practice: 1
Machine Learning 2
Prerequisites
• Good programming skills in Python
• Linear Algebra, Probability
• Artificial Intelligence
Machine Learning 3
Framework/Libraries
• NumPy, Pandas, Matplotlib: Python’s main scientific libraries.
• Scikit-Learn: implements many Machine Learning algorithms
• TensorFlow: train & run very large Neural networks
• Keras: high level Deep Learning API, simple to train & run
Neural networks, provides support for some advanced
TensorFlow features.
Machine Learning 4
References
[1]. Pattern Recognition and Machine Learning
[Christopher M.Bishop, 2006, Springer]
[2]. Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow
[Aurelien Geron, 2019, O’reilly]
[3]. Slides
[4]. Machine Learning (Andrew Ng): https://goo.gl/ WBwU3K
[5]. Machine Learning cơ bản: https://machinelearningcoban.com
Machine Learning 5
Grading
• On-going assessments:
• Diligence (D - attendance): 10%
• Labs (L - personal programming practice): 20%
• Middle Exam (ME - written exam): 20%
• Final Exam (FE- presentation based on project): 50%
• Total score = 0.1*D + 0.2*L + 0.2*ME + 0.5*FE
Machine Learning 6
Nhân bản – Phụng sự – Khai phóng
Enjoy the Course…!
Machine Learning 7
