CS 4787

CS 4787

Course information provided by the Courses of Study 2018-2019.

An introduction to the mathematical and algorithms design principles and tradeoffs that underlie large-scale machine learning on big training sets. Topics include: stochastic gradient descent and other scalable optimization methods, mini-batch training, accelerated methods, adaptive learning rates, parallel and distributed training, and quantization and model compression.

When Offered Spring.

Prerequisites/Corequisites Prerequisite: CS 4780 or CS 5780 or equivalent, CS 2110 or equivalent.

View Enrollment Information

Syllabi: none
  •   Regular Academic Session. 

  • 4 Credits Stdnt Opt

  • 17451 CS 4787   LEC 001

  • Enrollment limited to CIS students only. All others may add themselves to the waitlist during add/drop. Please go to http://www.cs.cornell.edu/courseinfo/enrollment for updates. It is expected that undergraduate students enroll in the 4000-level section of this class and graduate students enroll in the 5000-level section of this class.