2 code implementations • 25 Jun 2022 • Hajo Nils Krabbenhöft, Erhardt Barth
This paper presents TEVR, a speech recognition model designed to minimize the variation in token entropy w. r. t.
Ranked #1 on Speech Recognition on Common Voice German (using extra training data)
1 code implementation • NeurIPS Workshop SVRHM 2021 • Philipp Grüning, Erhardt Barth
Min-Nets are inspired by end-stopped cortical cells with units that output the minimum of two learned filters.
no code implementations • 9 Nov 2020 • Hammam Alshazly, Christoph Linse, Erhardt Barth, Thomas Martinetz
This paper explores how well deep learning models trained on chest CT images can diagnose COVID-19 infected people in a fast and automated process.
no code implementations • 18 Aug 2020 • Philipp Grüning, Thomas Martinetz, Erhardt Barth
Such FP-blocks are inspired by models of end-stopped neurons, which are common in cortical areas V1 and especially in V2.
no code implementations • 6 Oct 2017 • Lars Hertel, Erhardt Barth, Thomas Käster, Thomas Martinetz
Deep convolutional neural networks, trained on large datasets, achieve convincing results and are currently the state-of-the-art approach for this task.
Ranked #34 on Image Classification on MNIST
3 code implementations • EMNLP 2017 • Stanislau Semeniuta, Aliaksei Severyn, Erhardt Barth
In this paper we explore the effect of architectural choices on learning a Variational Autoencoder (VAE) for text generation.
2 code implementations • 2 Jun 2016 • Boris Knyazev, Erhardt Barth, Thomas Martinetz
In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently.
2 code implementations • COLING 2016 • Stanislau Semeniuta, Aliaksei Severyn, Erhardt Barth
This paper presents a novel approach to recurrent neural network (RNN) regularization.
no code implementations • 23 Jun 2014 • Bogdan Miclut, Thomas Kaester, Thomas Martinetz, Erhardt Barth
Deep convolutional neural networks are known to give good results on image classification tasks.
Ranked #98 on Image Classification on STL-10