Main Profile

At A Glance

Networks for Learning: Regression and Classification

During this course we will examine applications of several learning techniques in areas such as computer vision, computer graphics, database search and time-series analysis and prediction. Supervised learning with the use of regression and classification networks with sparse data sets will be explored. The extensivereading listgrounds the future researcher in the field of learning networks.Lecture notesprovide an overview of each topic covered in the class.The course focuses on the problem of...

Start Date: Feb 01, 2001 Topics: Computer Vision
Cost: Free

Contact

Networks for Learning: Regression and Classification's Full Profile

Overview

Description

During this course we will examine applications of several learning techniques in areas such as computer vision, computer graphics, database search and time-series analysis and prediction. Supervised learning with the use of regression and classification networks with sparse data sets will be explored. The extensivereading listgrounds the future researcher in the field of learning networks.Lecture notesprovide an overview of each topic covered in the class.The course focuses on the problem of supervised learning within the framework of Statistical Learning Theory. It starts with a review of classical statistical techniques, including Regularization Theory in RKHS for multivariate function approximation from sparse data. Next, VC theory is discussed in detail and used to justify classification and regression techniques such as Regularization Networks and Support Vector Machines. Selected topics such as boosting, feature selection and multiclass classification will complete the theory part of the course. During the course we will examine applications of several learning techniques in areas such as computer vision, computer graphics, database search and time-series analysis and prediction. We will briefly discuss implications of learning theories for how the brain may learn from experience, focusing on the neurobiology of object recognition. We plan to emphasize hands-on applications and exercises, paralleling the rapidly increasing practical uses of the techniques described in the subject.

Details

  • Dates: Feb 01, 2001 to May 25, 2001
  • Days of the Week: Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, Sunday
  • Level of Difficulty: Beginner
  • Size: Massive Open Online Course
  • Instructors: Dr. Alessandro Verri, Prof. Tomaso Poggio
  • Cost: Free
  • Institution: MIT OCW
  • Topics: Computer Vision

Provider Overview

About MIT OCW: MIT OpenCourseWare (OCW) is a web-based publication of virtually all MIT course content. OCW is open and available to the world and is a permanent MIT activity.

Latest Tweet

MIT OCW Offers Courses In: Computer

Questions about Networks for Learning: Regression and Classification

Want more info about Networks for Learning: Regression and Classification? Get free advice from education experts and Noodle community members.

  • Answer