Continually trained life-long classification

An incremental learning method with hybrid data over/down-sampling for sEMG-based gesture classification

“…In recent research, variations of the above approaches have been proposed under different situations [34][35]. However, algorithms based on these approaches were still in the exploration stage and most of them are applied to standard datasets such as MNIST, CIFAR10 [36][37][38]. Studies showed that these approaches can exhibit different or even conflicting results when utilizing different datasets or models [39,40].…”

A self-organizing world: special issue of the 13th edition of the workshop on self-organizing maps and learning vector quantization, clustering and data visualization, WSOM + 2019

“…Usually, this determination from the data partition dendrogram requires human expertise as input, especially in real application settings like the one which is the focus of the paper: decision support in an industry 4.0 environment, namely 3D printers based on sensor data in real-time. The final paper [10] takes us back to the problem of concept drift. Here, Szadkowski addresses, in a combined manner, two challenges for life-long classifiers: concept drift and catastrophic forgetting.…”