Continuous Mathematical Methods with an Emphasis on Machine Learning

CS205L

Stanford School of Engineering


Description

In this course, you’ll survey numerical approaches to the continuous mathematics used in computer vision and robotics—with an emphasis on machine and deep learning. Our focus will be on machine learning’s underlying mathematical methods, including computational linear algebra and optimization. Special topics will include automatic differentiation via backward propagation, momentum methods from ordinary differential equations, CNNs, and RNNs.
 

What you will learn

Note that this course replaces CS205A, and satisfies all similar requirements.
 

Prerequisites

Prerequisites: Math 51; Math 104 or 113 or equivalent or comfortable with the associated material.

Topics include

  • Computational linear algebra and optimization
  • Automatic differentiation via backward propagation
  • Momentum methods from ordinary differential equations
  • Conjugate gradient method
  • Ordinary and partial differential equations
  • Vector and tensor calculus
  • Convolutional neural networks

Course Availability

The course schedule is displayed for planning purposes – courses can be modified, changed, or cancelled. Course availability will be considered finalized on the first day of open enrollment. For quarterly enrollment dates, please refer to our graduate education section.

Thank you for your interest. The course you have selected is not open for enrollment. Please click the button below to receive an email when the course becomes available again.

Request Information