21 citations · 21 across the 2 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2019
Gradient-based training of Gaussian Mixture Models for High-Dimensional Streaming Data
Alexander Gepperth, Benedikt Pfülb
We present an approach for efficiently training Gaussian Mixture Model (GMM) by Stochastic Gradient Descent (SGD) with non-stationary, high-dimensional streaming data. Our training…
cs.LG2019★ 21 cited
Catastrophic forgetting: still a problem for DNNs
B. Pfülb, A. Gepperth, S. Abdullah +1
We investigate the performance of DNNs when trained on class-incremental visual problems consisting of initial training, followed by retraining with added visual classes. Catastrop…