PENG9560 Topics in Artificial Intelligence and Machine Learning Course description

This course covers advanced topics in artificial intelligence and machine learning, both theory and practice, recent scientific papers and state-of-the-art techniques.The course will be offered once a year, provided 3 or more students sign up for the course. If less than 3 students sign up for a course, the course will be cancelled for that year.

Basic background in statistics or probability theory. Knowledge of a programming language.

Students who complete the course are expected to have the following learning outcomes, defined in terms of knowledge, skills and general competence:

Knowledge

On successful completion of the course, the student has:

• an in-depth understanding of machine learning in its main forms: supervised, unsupervised, and reinforcement learning, both theoretical and applied, to solve real- lifeproblems.
• knowledge and understanding of the main concepts of deep learning.
• knowledge and understanding of some major concepts in artificial intelligence, including: complex systems (network models, cellular automata, and agent-based models) and evolutionary computing.

Skills

On successful completion of the course, the student can:

• apply techniques from machine learning to real-life problems.
• analyse data sets with the aid of machine learning algorithms.

General competence

On successful completion of the course, the student can:

• use libraries for programming deep learning algorithms such as TensorFlow.
• deploy models to relevant real-life problems.
• solve computational problem using evolutionary computing.

A real artificial intelligence project will be carried by a large team of students. A practical application will be targeted using state-of-the-art methods and tools. The students will construct a working system from scratch, implementing machine learning components as well as using existing tools. The students are involved in the entire process, starting from earlier design choices to the AI system completion. Examples of tasks may include speech processing and image recognition, robots or drones navigation, self-driving vehicles, chatbots, etc.

Through this course, the students will gain an in-depth understanding of "AI in practice", as opposed to "AI in theory" or "AI on toy problems".

Each module will be taught in a series of lectures. At the end of each module, the students will be assigned a small project to be submitted within a given deadline.

The following required coursework must be approved before the student can take the exam:

Compulsory assignments must be approved prior to the exam. The students must submit a small project at the end of each module. All five projects must be approved before examination.

Oral examination, individual.

The exam cannot be appealed.

None.

Pass or fail.

Two internal examiners. External examiner is used periodically.