0

(

ratings

)

2

students

Created by:

Profile Photo

Last updated:

October 13, 2022

Duration:

Unlimited Duration

FREE

This course includes:

Unlimited Duration

Badge on Completion

Certificate of completion

Unlimited Duration

Description

This course is for upper-level graduate students who are planning careers in computational neuroscience.

This course focuses on the problem of supervised learning from the perspective of modern statistical learning theory starting with the theory of multivariate function approximation from sparse data. It develops basic tools such as Regularization including Support Vector Machines for regression and classification. It derives generalization bounds using both stability and VC theory. It also discusses topics such as boosting and feature selection and examines applications in several areas: Computer Vision, Computer Graphics, Text Classification, and Bioinformatics. The final projects, hands-on applications, and exercises are designed to illustrate the rapidly increasing practical uses of the techniques described throughout the course.

Course Curriculum

  • The Course at a Glance Unlimited
  • The Learning Problem in Perspective Unlimited
  • Reproducing Kernel Hilbert Spaces Unlimited
  • Regression and Least-Squares Classification Unlimited
  • Support Vector Machines for Classification Unlimited
  • Manifold Regularization Unlimited
  • Unsupervised Learning Techniques Unlimited
  • Multiclass Unlimited
  • Ranking Unlimited
  • Boosting and Bagging Unlimited
  • Online Learning Unlimited
  • Generalization Bounds Unlimited
  • Stability of Tikhonov Regularization Unlimited
  • Uniform Convergence Over Function Classes Unlimited
  • Uniform Convergence for Classification Unlimited
  • Neuroscience Unlimited

About the instructor

5 5

Instructor Rating

1

Reviews

1520

Courses

1915

Students

Profile Photo
Massachusetts Institute of Technology