Teaching

Advanced Deep Learning

Modern architectures, representation learning, generative models and training at scale.

Large Language Models

Transformer architectures, pre-training and fine-tuning, prompting, alignment and evaluation of LLMs.

Computer Vision

Image formation, feature representation, deep models for recognition, detection and segmentation.

Introduction to Deep Learning

Foundations of neural networks: training and optimisation, core architectures and hands-on practice.

Applied Algorithms

Algorithm design paradigms, complexity analysis and practical problem solving.

Discrete Maths

Toán Rời Rạc

Logic, combinatorics, graph theory and the mathematical foundations of computing.

Scientific Computing

Tính toán khoa học

Numerical methods, approximation and simulation for engineering and science.

Introduction to Programming

First steps in programming: control flow, data structures and problem decomposition in Python.