Computer Science

This course introduces the basic theories, model architectures, algorithms, and implementation of deep learning for computer vision. Students obtain hands-on experience on implementing and training deep neural networks for computer vision tasks. The course covers the following topics: (1) neural network optimization algorithms; (2) backbone network architectures for computer vision, including convolutional neural networks and transformers; (3) network structure design for visual recognition tasks (image classification, object detection, image segmentation), and visual content generation tasks; (4) implementation and training of neural networks for computer vision tasks; (5) advanced topics in computer vision and deep learning. 

This course covers the tools and systems used to implement cloud computing systems, and presents key issues to be addressed, such as virtualization. Students learn cloud system platform technologies and detailed component technologies then configure servers and perform programming on public clouds like Amazon Cloud System (AWS) or Google Cloud System. 

Topics include Cloud computing concepts, Cloud computing models, Cloud computing architecture, Cloud computing platforms, Virtualization, Synchronization, Coordination, Distributed deadlock. 

This course covers machine learning techniques to analyze visual data. Specifically, this course focuses on fundamental machine learning and recent deep learning methods that are widely used in visual data analysis and discusses how these methods are applied to solve various problems with visual data. This course consists of lectures, practices, and projects. 

Topics include Introduction to CV/DL, Convolutional neural networks, Training, optimization, data, Few-shot learning, Object detection and segmentation, RNNS, Domain adaptation, Multimodal learning, Deployment. 

Prerequisite: Basic knowledge of Python 

In this course, students learn the process for how to design, build, test, deploy, maintain, and monitor scalable and robust data products using the Data Product Life Cycle (DPLC). Students gain hands-on experience working with datasets and use cases, collaborating in teams, and applying agile methodologies to deliver data products that meet the needs of real world stakeholders. The course covers the entire DPLC process, including experimentation and productization, with a focus on reliability, fault tolerance, scalability, deployment, and meeting regulatory requirements. The course prepares students for careers in data & digital technology, equipping them with the knowledge and skills required to work in cross-functional teams and navigate complex regulatory requirements.

This course explores mathematical concepts that are useful and frequently used in machine learning. Students examine linear algebra (vector spaces, scalar products, orthogonal vectors, matrices as linear mappings, determinants, eigenvalue and eigenvectors), analysis (differentiation), and probability theory (multidimensional probability distributions, calculations with expected values and variances). The class also discusses some contemporary applications of mathematics in machine learning. 

This course examines information technology infrastructure and security in the business environment. It covers the different components of IT infrastructure and security, as well as the best practices for designing, implementing, and managing secure systems.

This course aims to engender a mastery of the fundamentals of programming in C++, a language compiled to optimised machine-code, usable in a uniquely wide range of scenarios, from low level ‘close to the metal’ ones to ones involving high level programming abstractions. Command-line tools are used for program development so the module serves also as an introduction to that approach.

This advanced course introduces the basics of artificial intelligence, which include learning, searching, knowledge management, inference, and their applications. Transformer and Large Language Model are mainly discussed in addition to other types of deep neural networks. Classical artificial intelligence topics (before the deep learning era) is also overviewed. Applications to solve web, industrial, and scientific problems with artificial intelligence will also be introduced. 

Prerequisite: It is strongly recommended that students complete other basic machine learning and deep learning courses before enrolling in this course. The instructor reviews the basics of machine learning and deep learning, but it is not a guarantee that the review will be enough for students who did not previously take any related courses.  

In this course, students learn how to use Python to retrieve and parse data from biological repositories through bulk download and application programming interfaces (APIs). They learn about established data formats for different data modalities so that they understand the structure and content of the data they are using and how it was generated. Each week students focus on analytical tasks in linked topics that span the main components of modern biomedical informatics research. Topics change slightly each year, but typically include tools, algorithms, and approaches for biological sequence, multi-omics (transcriptomics, proteomics, methylomics), biomedical network, and biomedical text analysis. Each topic is explored using real-world examples.

 

This course focuses on Deep Learning (DL), with an emphasis on recent advances in Natural Language Processing (NLP). It is structured into lectures that cover the fundamental concepts of the field, complemented by practical tutorials and exercises, where these concepts are further expanded and practically implemented through live coding sessions (mainly in Python). The course is organized along the following themes: Recap of Machine Learning (ML) fundamentals; Introduction to Neural Networks and the connectionist paradigm: from the perceptron to Multi-Layer Perceptrons (MLPs), universality theorems, the backpropagation algorithm, and principles of Neural Network design; The rise of Deep Learning: Convolutional Neural Networks (CNNs), regularization techniques, and residual connections. Basics of Recurrent Neural Networks (RNNs), attention mechanisms, and Transformers; Introduction to Natural Language Processing (NLP): text preprocessing, static and contextual word embeddings, language modelling, and neural approaches to text processing—from neural machine translation to modern large language models (LLMs). Course prerequisites: solid understanding of calculus, linear algebra, probability, and statistics, along with basic prior programming experience in Python.