MSc:AdvancedMachineLearning old

Advanced Machine Learning

• Course name: Advanced Machine Learning
• Course number: DS-02
• Area of instruction: Computer Science and Engineering

Administrative details

• Faculty: Computer Science and Engineering
• Year of instruction: 2nd year of MSc
• Semester of instruction: 2nd semester
• No. of Credits: 5 ECTS
• Total workload on average: 180 hours overall
• Frontal lecture hours: 2 hours per week.
• Frontal tutorial hours: 0 hours per week.
• Lab hours: 2 hours per week.
• Individual lab hours: 2 hours per week.
• Frequency: weekly throughout the semester.
• Grading mode: letters: A, B, C, D.

Course outline

This course is designed for graduate students to provide comprehensive and advance topics in machine learning. Student will learn to implement the machine learning models in Python programming environment from data science prospective. In this course, we will cover sampling methods, Splines, Kernel Hilbert spaces, Neural Network Architectures (CNN, LSTM, Attention, RNN), Regularizations, Bayesian Learning and networks, Graphical Models (HMM), Autoencoders, Generative models, Reinforcement learning and Collaborative filtering. The end of the day they will able to apply machine learning algorithms to solve real-world problems.

Expected learning outcomes

• Understand how machine can learn the concepts
• Significant exposure to real-world implementations
• To develop research interest in the theory and application of machine learning

Programming related learning outcomes

• The course include a significant amount of programming in Python, which the student needs to master during the labs and project.
• Each student team will develop a project written in Python with the help of machine learning libraries.

Required background knowledge

An overview of artificial intelligence fundamentals and Python programming skills would be a plus point, but not required.

Prerequisite courses

As a graduate level course, the students are expected to have engineering undergraduate background. Familiarity with basics concepts of probability, linear algebra and basics of machine learning.

Detailed topics covered in the course

• Introduction to Advanced Machine Learning
• Neural Network Architectures: CNN and Training Nets
• Recurrent Neural Networks, LSTM, Attention
• Splines and GAMs
• Evolutionary Computations – Genetic Algorithms
• Bayesian Learning – Bayes Theorem and Bayes Network
• Graphical Models – Hidden Markov Model
• Autoencoders – Variational autoencoder, inference, applications
• Collaborative Filtering
• Generative Models – GAN
• Reinforcement Learning – Q learning, deep learning

Textbook

• Handouts supplied by the instructor
• Materials from the interment and research papers shared by instructor

Required computer resources

Student should bring laptop machine in the class.

Evaluation

• Quiz (10%)
• Group project (20%)
• Lab participation (20%)
• Mid-term exam + Lab (20% + 5%)
• Final exam + Lab (20% + 5%)