Note

Visual Intelligence publications are financially supported by the Research Council of Norway, through its Centre for Research-based Innovation funding scheme (grant no. 309439), and Consortium Partners.   

Note

Visual Intelligence publications are financially supported by the Research Council of Norway, through its Centre for Research-based Innovation funding scheme (grant no. 309439), and Consortium Partners.   

Scientific publications

Visual Intelligence will work across the innovation areas to extract information from large volumes of visual data more efficiently through automatic and intelligent data analysis. The core research challenges in deep learning: working with limited training data, utilizing context and dependencies, providing explainability, confidence and uncertainty, are important in all the innovation areas.

publications as of January 2021:
February 19, 2021
·
Shujian Yu, Francesco Alesiani, Xi Yu, Robert Jenssen, Jose Principe

Measuring Dependence with Matrix‐Based Entropy Functional

Published to AAAI-21. An interpretable and differentiable dependence (or independence) measure that can be used to 1) train deep network under covariate shift and non-Gaussian noise; 2) implement a deep deterministic information bottleneck; and 3) understand the dynamics of learning of CNN. Code available.

Areas:
Explainability and reliability
Confidence and uncertainty