Academy of Finland
Funding decision
 
Name Pahikkala, Tapio
Organisation University of Turku
Project title Tensor-Based Machine Learning for Big Data with Inherent Dependencies
Decision No. 311273
Decision date 20.06.2017
Funding,period 01.09.2017 - 31.08.2021
Funding 370 741
WebFOCUS Report
Project description
Machine learning (ML) has recently achieved a lot in areas where the standard assumptions about the data hold and the amount of training data available is large. However, it still faces many challenges in areas where we would need it the most. The commonly made independently and identically distributed (IID) assumption about data is rarely holds in practice, violating the guarantees about ML methods relying on the assumption. In this proposal, novel tensor-based ML methods turn the IID violations into our advantage so that both sample complexity and computational complexity are decreased, and the reliability of the prediction performance estimates are improved. Immediate applications include zero-shot learning in general, ML in domains with highly-structured data in particular. The applicants' track record in applied research already covers a large array of examples in which the preliminary steps of this research direction has been shown to be highly successful.