Deep Learning

Catalog description

This course offers a comprehensive introduction to the fundamental principles, theories, and practical aspects of deep learning. Lectures will begin with the basics of shallow neural networks before progressing to complex deep neural network structures. The topics include an overview of key neural network architectures, such as convolutional, recurrent, and autoencoder networks, and their applications in computer vision for tasks like image classification and segmentation, as well as in natural language processing for text classification and machine translation. Additionally, students will learn to craft deep learning architectures using Python on open-source machine learning platforms. Through a combination of lectures, practical exercises, and final projects, students will acquire the ability to implement deep learning models in real-world situations. Undergraduate Equivalent: CPSC 4366 .