This course covers the theory and practice of deep learning and neural networks. Topics covered include training methods and loss functions, automatic differentiation and backpropagation, network architectures for different learning problems, validation, model selection and software tools.
Prerequisites: EECS 5327 or EECS 6327 or permission of instructor
Tips: you can drag and drop the boxes to clone them to different sections or groups within a prerequisite equation.
Prerequisite Equation
Edit the prerequisite equation to this course:
note: adding data in this section will override data in the Prerequisite List.
+ add prereq equation
Prerequisite List(Overridden by Prerequisite Equation)
Edit the list of prerequisites to this course:
note: data in this section will be override by the Prerequisite Equation if it exists.
+ add new course
Exclusion List
Edit the list of course cerdit exclusions to this course:
+ add new course
Your name (optional):
Any additional comment (optional):
Thank you for your edit suggestion!
Our staff will review and approve it soon.
You can close this page now.
There might have been an error with the server or your input.
Please check your entry and/or try again later.