Principles of Deep Learning

Catalog description

Credits 3. 3 Lecture Hours. Theory and practice of deep learning, including topics concerning approximation, generalization and optimization; study of the theory of universal approximation, stochastic gradient-based optimizers and statistical learning bounds, but also computational aspects including backpropagation and batch normalization. Prerequisite: MATH 304 , MATH 251 , MATH 411 , and MATH 679 or equivalent; or approval of instructor.