activity
20192021
most citedContinual Learning with Fully Probabilistic Models

4 citations · 4 across the 1 of their papers we have counts for

collaborators

6 papers

cs.CV2021

Image Modeling with Deep Convolutional Gaussian Mixture Models

Alexander Gepperth, Benedikt Pfülb

In this conceptual work, we present Deep Convolutional Gaussian Mixture Models (DCGMMs): a new formulation of deep hierarchical Gaussian Mixture Models (GMMs) that is particularly…

cs.LG20214 cited

Continual Learning with Fully Probabilistic Models

Benedikt Pfülb, Alexander Gepperth, Benedikt Bagus

We present an approach for continual learning (CL) that is based on fully probabilistic (or generative) models of machine learning. In contrast to, e.g., GANs that are "generative"…

cs.LG2021

Overcoming Catastrophic Forgetting with Gaussian Mixture Replay

Benedikt Pfülb, Alexander Gepperth

We present Gaussian Mixture Replay (GMR), a rehearsal-based approach for continual learning (CL) based on Gaussian Mixture Models (GMM). CL approaches are intended to tackle the pr…

cs.LG2020

A Rigorous Link Between Self-Organizing Maps and Gaussian Mixture Models

Alexander Gepperth, Benedikt Pfülb

This work presents a mathematical treatment of the relation between Self-Organizing Maps (SOMs) and Gaussian Mixture Models (GMMs). We show that energy-based SOM models can be inte…

cs.LG2019

A Study of Deep Learning for Network Traffic Data Forecasting

Benedikt Pfülb, Christoph Hardegen, Alexander Gepperth +1

We present a study of deep learning applied to the domain of network traffic data forecasting. This is a very important ingredient for network traffic engineering, e.g., intelligen…

cs.LG2019

A comprehensive, application-oriented study of catastrophic forgetting in DNNs

B. Pfülb, A. Gepperth

We present a large-scale empirical study of catastrophic forgetting (CF) in modern Deep Neural Network (DNN) models that perform sequential (or: incremental) learning. A new experi…