73 citations
- Transylvania University of BrașovRO6 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- Nagoya City UniversityJP2 papers
- National Astronomical Observatory of JapanJP2 papers
- Siemens (Romania)RO2 papers
- Université Paris CitéFR2 papers
- Arcetri Astrophysical ObservatoryIT1 paper
- Astrophysique, Instrumentation et ModélisationFR1 paper
- California Polytechnic State UniversityUS1 paper
- CEA Paris-SaclayFR1 paper
- Center for Astrophysics Harvard & SmithsonianUS1 paper
- Chinese Academy of SciencesCN1 paper
23 papers
Boosting of Classification Models with Human-in-the-Loop Computational Visual Knowledge Discovery
Alice Williams, Boris Kovalerchuk
High-risk artificial intelligence and machine learning classification tasks, such as healthcare diagnosis, require accurate and interpretable prediction models. However, classifier…
Synthetic Data Generation and Automated Multidimensional Data Labeling for AI/ML in General and Circular Coordinates
Alice Williams, Boris Kovalerchuk
Insufficient amounts of available training data is a critical challenge for both development and deployment of artificial intelligence and machine learning (AI/ML) models. This pap…
Learning in Convolutional Neural Networks Accelerated by Transfer Entropy
Adrian Moldovan, Angel Caţaron, Răzvan Andonie
Recently, there is a growing interest in applying Transfer Entropy (TE) in quantifying the effective connectivity between artificial neurons. In a feedforward network, the TE can b…
Crypto Technology -- Impact on Global Economy
Arunkumar Velayudhan Pillai
The last decade has been marked by the evolution of cryptocurrencies, which have captured the interest of the public through the offered opportunities and the feeling of freedom, r…
Model Uncertainty and Selection of Risk Models for Left-Truncated and Right-Censored Loss Data
Qian Zhao, Sahadeb Upretee, Daoping Yu
Insurance loss data are usually in the form of left-truncation and right-censoring due to deductibles and policy limits respectively. This paper investigates the model uncertainty…
Learning in Feedforward Neural Networks Accelerated by Transfer Entropy
Adrian Moldovan, Angel Caţaron, Răzvan Andonie
Current neural networks architectures are many times harder to train because of the increasing size and complexity of the used datasets. Our objective is to design more efficient t…