Goal:
The goal of this course is to provide students with a solid foundation in deep learning, covering both theoretical principles and practical applications. Students will learn how to design, train, and evaluate deep neural networks, understand the mathematical foundations behind key algorithms, and explore state-of-the-art architectures such as convolutional networks, recurrent networks, autoencoders, and generative models.
Course description:
This course introduces the fundamental concepts, architectures, and algorithms of deep learning. Topics include feedforward networks, optimization methods, regularization, convolutional and recurrent neural networks, autoencoders, and generative models. Emphasis is placed on both theory and practice: students will gain mathematical intuition about why deep learning methods work, as well as hands-on experience implementing and training models.