Machine Learning has become an important aspect the digital world and has been essential to the
success of many application areas such as autonomous driving, object recognition and detection,
anomaly or fraud detection, recommender system, speech recognition, and sentiment analysis, to
name a few. Machine learning is able to extract hidden patterns/features from raw data and learns
from experience without being explicitly programmed.
This course will familiarize students with the fundamental concepts, theories, and practical
algorithms of deep/machine learning to enable students to gain the necessary knowledge for their
future industry job/research. Moreover, this course will also introduce students about the latest and
powerful technology called deep learning, which is a subset of machine learning, and it also
prepares students for future research or career in any technology industries.
This course is organized as follows:
o Lessons will be conducted by the lecturer either online, offline, or both, depending on real
circumstances. Google Meet or any other suitable tools will only be used for the online
class. Students must be actively participating in the class.
o Individual and Team Work:
▪ Individual quizzes and small group assignment will be given to students throughout
the course.
▪ Students will be divided into small teams which consist of 3-4 students or more than
that depending on number of students in the class. Each team should have a unique
project assignment. Each student must actively participate in every project
1
activity. Lecturer will advise students for each assignment or project when
necessary.
o Final Project:
o There is a final project which each team need to submit a project proposal and
perform project presentation and demo after project completion at the end of the
course. Each team will then submit a final project paper similar to conference or
journal paper (a template will be provided).
By the end of this course, students should be able to:
LO1: Get to know each other and understand the course syllabus. Understand machine learning
concepts, roadmap and challenges, domain areas, and its real-world applications.
LO2: Understand basic linear algebra applied in machine learning such as vector, matrix,
tensor operation, and derivatives. Understand major Python functions and useful
tools for machine learning.
LO3: Understand common machine learning algorithms/libraries and datasets. Implement
machine learning algorithm with real datasets.
LO4: Understand image classification problem and linear classifier. Understand loss
function, optimization, and backpropagation.
LO5: Understand basic concepts of artificial neural network and how biological neurons and
neural networks is mapped to artificial neurons. Understand the convolutional
neural network in deep.
LO6: Understand biological neurons and neural networks of human brain. Understand how
neural networks of human brain are mapped to artificial neural networks. Train neural
network algorithms and improve the training algorithms.
LO7: Understand the Keras Deep Learning framework which is a high-level framework.
Present and demo a small group assignment and receive feedbacks.
LO8: Understand the Keras Learning framework in deep.
LO9: Understand popular deep learning architectures and compare deep learning
algorithms. Train deep learning algorithms with the pre-trained models.
LO10: Written Exam.
LO11: Understand how to use google cloud to speed up the learning process and compare the
speed. Understand transfer learning and fine-tuning the models. LO12: Understand model
ensemble to successfully build state-of-the-art models. Create and deploy trained models to
the web.
LO13: Understand the tips and tricks to successfully train deep learning models.
2
LO14: Present and demo the final project. Create project papers similar to conference/journal
paper in deep/machine learning domain which lead toward successful
journal/conference publication.
LO15: Wrap-up what have been learned and submit project materials.