Algebraic Representation Learning
We open an opportunity with our support for those computer scientists in the master level who have been a big fan of mathematics, however could not find a strong bridging of this knowledge and interest in AI so far. The idea is to connect known mathematical theories in Today’s AI. For example the use [...]
Smart Analytics on Environmental, Medical or Scholarly Graphs using Knowledge Graph Embedding
There are a huge number of knowledge graphs available for AI-related applications such as smart analysis, link prediction, and recommendation. We focus on three major domains of Environmental, Medical or Scholarly domains and their available datasets. We plan to use embedding models in order to provide smart analytics and link prediction services on them. [...]
Geometric Neural Networks
Neural Networks have shown promising performance in various tasks including classification, regression and clustering. Performance of NNs depends on the underlying geometry they designed on. However, most NNs are designed while they are unaware of the data geometry. We aim at tackling this problem and developing new NNs based on recent findings in geometry [...]