no code implementations • 12 Jul 2022 • Benedikt Pfülb
This dissertation is set in the context of continual machine learning with deep learning methods.
no code implementations • 19 Apr 2021 • Benedikt Pfülb, Alexander Gepperth, Benedikt Bagus
As a concrete realization of generative continual learning, we propose Gaussian Mixture Replay (GMR).
no code implementations • 19 Apr 2021 • Benedikt Pfülb, Alexander Gepperth
In addition, task boundaries can be detected by applying GMM density estimation.
no code implementations • 19 Apr 2021 • Alexander Gepperth, Benedikt Pfülb
For generating sharp images with DCGMMs, we introduce a new gradient-based technique for sampling through non-invertible operations like convolution and pooling.
no code implementations • 24 Sep 2020 • Alexander Gepperth, Benedikt Pfülb
This work presents a mathematical treatment of the relation between Self-Organizing Maps (SOMs) and Gaussian Mixture Models (GMMs).
1 code implementation • 18 Dec 2019 • 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.
no code implementations • 25 Sep 2019 • Alexander Gepperth, Benedikt Pfülb
We present an approach for efficiently training Gaussian Mixture Models (GMMs) with Stochastic Gradient Descent (SGD) on large amounts of high-dimensional data (e. g., images).
no code implementations • 10 Sep 2019 • Benedikt Pfülb, Christoph Hardegen, Alexander Gepperth, Sebastian Rieger
We present a study of deep learning applied to the domain of network traffic data forecasting.