CS-E4890 - Deep Learning, 26.02.2019-31.05.2019

Topic outline

• Project work
  • Select activity The idea of the project work to use the knowledge ...

    The idea of the project work to use the knowledge that you have gained during the course to solve real life problems. Additionally, you are expected to report your work in a similar manner as you do in a scientific publication (with a considerably smaller scope). Together with your group, you are expected to consider a suitable challenge, choose what type of deep learning model would be suitable, make the implementation and report your findings. We will offer you pointers to various datasets that can be used in your project. You are not limited to any particular data, a deep network structure or a computational environment.

    Instructions for selecting a topic for the project

    The topic your group selects should be such that it is interesting and challenging, but not too challenging so that you can accomplish it all (literature survey, code writing, debugging, experimenting, reporting) in 30 hours per student. It is advisable to select a topic and research problem for which there exist a well-defined evaluation scheme and reference results you can compare against.

    The project proposals should be submitted using the tool on this web page.

    Notice: If you already have done or are currently doing a similar project in another course, it is not acceptable to report the same project in this course!

    Teams

    You can do your project alone or in a team. The recommended size of a team is two people but I can accept teams with three people if you convince me that the project is challenging enough. You need to declare your team when you submit the project proposal.

    Web resources for the project

    There are good resources in the web where you can find problems and datasets for your deep learning research. These include but are not limited to:

    • ImageNet
    • Kaggle
      
    • Street View House Numbers (SVHN)
      
    • CIFAR datasets
      
    • Movie review dataset 
      
    • grand-challenge.org
      
    • UCI machine learning repository
      
    • YELP
      
    • Product review databases, e.g. Amazon reviews
      
    • Stanford Sentiment Treebank
      
    • Texture datasets Brodatz, OuTex, KTH-TIPS
      
    • Microsoft COCO
      
    • Berkeley segmentation datasets
      
    • List of datasets in Wikipedia
      
    • List of datasets in deeplearning.net
      

    Reporting the results of your project

    The instructions for the structure of the report will be posted later.

    Schedule

    • Thursday 18.04.2019 deadline for submitting project proposals in MyCourses
      
    • Sunday 19.05.2019 deadline for submitting project reports
      
    • Friday 24.05.2019 deadline for peer-grading of project works
      

  • Select activity Submit your project proposal

    

    Submit your project proposal Assignment
  • Select activity Evaluation formBelow is a draft of the evaluation ...

    Evaluation form
    

    Below is a draft of the evaluation form that will be used in peer assessment of the project works. We recommend you to look at the form before writing your project report.
    

  • Select activity Evaluation form for peer assessment of project works

    

    Evaluation form for peer assessment of project works File TXT
  • Select activity Instructions for submission of project reportsIn o...

    Instructions for submission of project reports

    In order to submit your project reports, please go to www.peergrade.io/join and use class code C58SFZ