Lecture: Deep Learning for Visual Recognition

Course

  • Lecturer(s):
  • Start: 18.10.2017
  • Dates: Wed. 10:15 - 11:45, LBH / HS III.a
  • Course number: MA-INF 2313
  • Curriculum: Master
  • Effort: 6 CP

Exercises

Description

Neural networks are making a comeback!  Deep learning has taken over the machine learning community by storm, with success both in research and commercially.  Deep learning is applicable over a range of fields such as computer vision, speech recognition, natural language processing, robotics, etc.  This course will introduce the fundamentals of neural networks and then progress to state-of-the-art convolutional and recurrent neural networks as well as their use in applications for visual recognition.  Students will get a chance to learn how to implement and train their own network for visual recognition tasks such as object recognition, image segmentation and caption generation.

No formal pre-requisites.  Students should already be comfortable with concepts in probability theory and optimization and are recommended to have taken at least one course in machine learning or computer vision.  Exercises will be a mix of theory and practical (Python).

News

Instructions for accessing the GPU server for the projects have been posted online under Additional Documents (DL2017 ServerInfo). You have to pick up access codes in person. On Thursday (Dec. 07) from 11:00 - 12:00, you can stop by I.81 and get your credentials. Or on Friday (Dec. 08) from 16:30 - 18:00, you can get your credentials during the exercise hours in LBH III.a. Please try to log on asap; if the account does not work, please contact the TAs.

Projects : In this google sheet externhttps://docs.google.com/spreadsheets/d/1WZv-gyKdLtyFi1-h0n9_gdH4UNya5YjqpQbM7uQggQM/edit?usp=sharing, on the first sheet you will find your group names and team-mates. In the second sheet, you will find a list of the available GPU slots. Follow the instructions on that page to choose your slots. Access codes will be handed out once the slots have been allotted. The instructions for using the GPU server will be shortly on the course website under the 'Additional Documents’ section. 

There is no lecture on December 6 due to Dies Academicus!

Please note that there will be a lecture on November 29.

Course projects announced today (24 Nov. 2017). The projects will be allocated on a first come first serve basis. If you don't know how to sign up for a project and a presentation date, please email the TAs.

Please note that there will be a lecture on Oct. 20 during the exercise slot.

First lecture starts on October 18, 2017. See you there!

Please inscribe yourself into the mailinglist at: externhttps://lists.iai.uni-bonn.de/mailman/listinfo.cgi/vl-dl
In case you have a problem understanding something, questions related to  exercises/projects, please always feel free to write to the mailing list. This should be a place where you students can talk freely about the lecture, so please do not hesitate to ask and reply!

Additional Documents

Slides

Assignment Sheets

Exercise 1: MLbasics
Assignment sheet  (PDF document, 170 KB)
Exercise 2: NNintro
Assignment sheet  (PDF document, 123 KB)
Exercise 3: DeepOptReg
Assignment sheet  (PDF document, 139 KB)
Exercise 4: CNNs
Assignment sheet  (PDF document, 136 KB)