Persönlicher Status und Werkzeuge

Home Teaching Winter Semester 2016/17 Practical Course: Hands-on Deep Learning for Computer Vision (6h / 10 ECTS)

Practical Course: Hands-on Deep Learning for Computer Vision (6h / 10 ECTS)

WS 2016, TU München


Please direct ALL questions regarding this practical course at dlpractice[at]vision.in.tum.de

Lecturer: Dr. Laura Leal-Taixe

Tutors: Caner Hazirbas, Vladimir Golkov

The course will start on 18.10.16 Tuesday at 16:00 in room 02.09.023.

Course Description

In this course, we will develop and implement deep learning algorithms for concrete applications in the field of computer vision. The main purpose of this course is to gain practical experience with the most successful machine learning tool in computer vision since 2012, and to learn about its benefits and drawbacks when applied to concrete, relevant problems.

Important Announcement

Thank you all for your interest. Our course capacity is now full. All students in the waiting list must present in the first lecture. We will give the free spots based on the order.

Preliminary meeting will take place on 21th June 2016, Tuesday between 16:00 and 16:45 in room 02.09.023.

Slides of the pre-meeting can be found here.

The course registration is done via the matching system. Please only register on TUMOnline if you are assigned the course.

Requirements: Passion for mathematics and the use of machine learning in order to solve complex computer vision problems. The course will be focused on practical projects, therefore, previous knowledge of Python is desired.

Number of participants: max. 27

Course Structure

In the first three weeks, there will be lectures and exercise sheets handed out every week, containing practical/theoretical problems. After that, the students will work in groups on practical machine learning problems in computer vision. Each group consists of 2 students, and will be supervised by one of the lecturer/tutors. During the remaining of the semester, the group meet weekly with their supervisor to discuss the project progress. At the end of the semester, each group will present their project with a following Q&A section. There will be no additional written or oral exam. Both theoretical and practical part will be considered in the final grading. The course schedule are detailed below.

Course Schedule

Lectures will be held on Tuesday between 16:00 and 17:45 in room 02.09.023.

  • 18.October : Intro to Feedforward and Recurrent Neural Networks
  • 25.October : Convolutional Neural Networks and project presentations
  • 08.November : Convolutional Neural Networks cont.
  • tba : Final Presentations
Course Materials

Please find the slides on the course material page.

Literature

  • Kevin Murphy. “Machine Learning: A Probabilistic Perspective”, MIT Press, Cambridge, Massachusetts 2012,
  • Christopher M. Bishop. “Pattern Recognition and Machine Learning”, Springer, Berlin, New York, 2006.
Last edited 24.10.2016 22:24 by Caner Hazirbas