Round Corner
Department of Computer and Information Science


Data/Resource Efficient Deep Learning [2019/2020] [Norwegian OpenAI Lab]


[Project in collaboration with Norwegian OpenAI Lab]



(More detailed information at the following LINK)

Deep Learning has been shown to outperform most of the previous machine learning techniques in the supervised learning area, mostly in the computer vision domain and in many Natural Language processing tasks. In real scenario it’s often difficult to have such amount of available data and it is expensive to collect them as well guarantee quality.

To tackle this problem different techniques/area of research are explored:

- Transfer learning + Lifelong/Continual Learning
- Few-Shot Learning
- Data Augmentation and GAN
- Self-Supervised Learning
- Active Learning
- Weak Supervision
- Multitask Learning

The students will get familiar with state-of-the-art within one or more areas mentioned and will focus on a specific research problem.


Interesting Workshops
Continual Learning WS (Neurips2018)
Learning with Limited Labelled Data (ICLR2019)





Massimiliano Ruocco Massimiliano Ruocco
Adjunct Associate Professor
248 IT-bygget
NTNU logo