Andrei Stoian

Regularization Shortcomings for Continual Learning

2019 · arXiv (Cornell University)

In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are challenged, leading to the famous phenomenon of catastrophic forgetting. …

Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems

2019 · Preprints.org

The Sentinel-2 satellite mission offers high resolution multispectral time series image data, enabling the production of detailed land cover maps globally. At this scale, the trade-off between processing time and result quality is a central …