In this course, students master the most important skills needed in modern artificial intelligence (AI) workplace. These skills include mastery of PyTorch framework for construction of deep learning models (neural networks), mastery of AI assisted Python programming and basic agentic application development. We demonstrate that deep learning is a most powerful technique for data analysis and solution for many complex problems in sciences, linguistics, and engineering. We demonstrate deep learning for classification and generation of images, speech recognition and speech synthesis, natural language translation, sound and music manipulation, navigation of self-driving cars, and several other activities. Students master key deep learning architectures, such as convolutional neural networks (CNNs), autoencoders (AEs), variational autoencoders (VAEs), stable diffusion, and graph neural networks (GNNs). We introduce transformers with attention as the building blocks of large language models, the basis of modern generative AI. Students learn how to enhance Python code with AI code generators. The course starts with a review of the theoretical foundations of neural networks including auto-differentiation and backpropagation. The emphasis is on practical development of deep learning models and applications with Python and PyTorch.
Credits: 4
View Tuition InformationTerm
Fall Term 2026
Part of Term
Full Term
Format
Flexible Attendance Web Conference
Credit Status
Graduate, Noncredit, Undergraduate
Section Status
Open