Deep Learning

Deep Learning delves into the fundamental principles, underlying mathematics, and implementation details of deep learning. The curriculum is designed to provide a robust understanding of the core concepts and methodologies essential for optimizing highly parameterized models. Key topics include gradient descent, backpropagation, and the broader framework of computation graphs. The course explores the essential modules that constitute deep learning models, such as linear, convolution, and pooling layers, along with various activation functions. The course also covers common neural network architectures, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), equipping students with the skills needed to design, implement, and optimize advanced deep learning systems. Through hands-on projects and practical applications, the course prepares students to gain the expertise to tackle real-world challenges using deep learning techniques.

Official catalog text — WGU-authored.