Machine Learning

SPECIALIZATION ELECTIVE

Credit Hour : 3

Pre-requisite: Mathematics for Machine Learning

Synopsis

Machine learning is the science of getting computers to act without being explicitly programmed. In this course, the students will learn about the available machine learning techniques and gain practice implementing them. This course mainly introduces the main concepts of machine learning, the classification of machine learning, the overall process of machine learning, and the common algorithms of machine learning. More importantly, the student will learn about not only the theoretical underpinnings of learning but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. This course provides a broad introduction to machine learning. In addition, it describes the basic knowledge of deep learning, including the development history of deep learning, components and types of deep learning neural networks, and common problems in deep learning projects. The course will also draw from numerous case studies and applications so that the student will also learn how to apply learning algorithms to solve various real-world problems.

Course Content

Topic 1: Machine Learning Concepts and Best Practices

Types of Learning (supervised, unsupervised, semi-supervised, reinforcement learning)
Example real-world applications
Basic Machine Learning Concepts and Process (dataset, data processing, data cleansing, data conversion, feature selection)
Machine-learning System Development
Model Evaluation (model validity and capacity, bias and variance theory, performance evaluation for regression, performance evaluation for classification)
Other key machine learning methods (Machine Learning Training Method-Gradient Descent; Parameters and Hyperparameters in Models, Hyperparameter Searching Method, Cross-validation)

Topic 2: Common Machine Learning Algorithms

Classification (Logistic Regression, Decision Trees, Naive Bayes, Support Vector Machine (SVM), k-nearest neigbours (kNN), Neural Networks, Deep Learning for Classification, Ensemble Learning)
Regression (Linear Regression, Decision Trees, Support Vector Regression, Lasso Regression, Random Forest, Deep Learning for Regression)
Ensemble Learning
Basic of Clustering Algorithms

Topic 3: Deep Learning

Deep learning Summary
Training Rules
Activation Function
Normalizer
Optimizer
Types of Neural Network
Common Problems
Easier-to-Use Development Framework

References

Russell, S. J., Norvig, P., & Davis, E. (2020). Artificial intelligence: a modern approach. 4th ed. Upper Saddle River, NJ: Prentice Hall.

Huawei HCIA-AI Course Module

Prepared By:

Assoc. Prof. Ts. Dr. Amiza Amir

Page updated

Report abuse