Recent ProfessorsNot yet assignedRecent SemestersNo scheduled sections on recordClass SizeNot publishedCredits3PrerequisiteCompletion with a C or better in: AI 5 Transfers ToNot transferableDescriptionThis course provides a comprehensive introduction to the principles, mathematics, and implementation techniques that underpin modern deep learning. Students gain a solid foundation in core concepts such as gradient descent, back propagation, computation graphs, and optimization of highly parameterized models. The course examines the essential building blocks of neural networks including linear, convolutional, and pooling layers, as well as common activation functions. The course introduces widely used architectures such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). Through hands-on labs and real-world applications in vision, language, and generative modeling, students learn to design, implement, train, and evaluate advanced deep learning systems. 