TNT logo Zur zentralen Website der Leibniz Universität Hannover Bannerlogo des Instituts für Informationsveratbeitung
Masterarbeit, Studienarbeit:

ORKG4NAS: Open Research Knowledge Graph for Neural Architecture Search

Im Rahmen des Projekts AutoML

Beschreibung

Applying deep learning to new tasks often also requires new architectures of deep neural networks to achieve top performance. However, finding such architecture is often a tedious and error-prone task for human developers. The field of neural architecture search (NAS) addresses this challenge by studying different ways of automatically finding optimal architectures. By now, there are roughly 300 papers on NAS. Searching in these many papers became quite tedious over time and the number of published papers in this field is still growing. In this project, we will study whether we can make use of an open research knowledge graph (ORKG) to better structure the literature on NAS. The big open question here will be how to build useful structures and how to connect papers with each other such that we can extract new trends and insights from these papers. If the project will be successful, it will be a huge benefit for the NAS community.

Voraussetzungen

We strongly recommend that students should have experience for the following topics:

To apply for this project, please send us an email with the following information:
  1. Which ML-related courses have you taken?
  2. Can you please attach your transcript of records?
  3. Which projects have you done so far (in Hannover and elsewhere)?
  4. Which topics interest you most?


  5. Since different projects require different skill sets, please also rate your skills in the following categories on a scale from ++ (very good) to -- (no knowledge/skill):
  6. Creativity / ideas for developing new algorithms
  7. Getting someone else's large code base to run
  8. Running comprehensive experimental studies / keeping track of results
  9. Self-motivation to push through even if things don't work for a while
  10. Coding skills
    1. Python
    2. TensorFlow
    3. Keras
    4. PyTorch
    5. C/C++
  11. Ability to read a RL paper, implement it and get it to work
  12. Ability to read a DL paper, implement it and get it to work
  13. Ansprechpartner: Marius Lindauer