The course introduces Deep Learning (DL) basics, methods, and algorithms, with hands-on practice using modern DL library tools (e.g., PyTorch). After the introductory lecture on deep learning, the course first covers the fundamental of neural networks, including universal approximator theory, learning neural networks, backpropagation, optimization, stochastic gradient descent, and tricks on training neural networks, and then focuses on typical neural network architectures, including Convolutional Neural Networks, Recurrent Neural Networks, and Generative Neural Networks.

CILO-1: Apply the theories and fundamentals of Deep Learning (DL) to define and formulate DL problems. CILO-2: Apply different DL methods, algorithms, and techniques to solve DL problems. CILO-3: Use modern DL library tools (PyTorch) to implement and fine-tune different DL models. CILO-4: Design and implement coding solutions to solve real-world DL problems.