219 citations · 249 across the 14 of their papers we have counts for
16 papers
Patient Pose Assessment Using a CT-Based Framework for Synthetic Data Generation
Manuel Laufer, Dominik Mairhöfer, Malte Sieren +7
An adequate diagnostic quality of radiographs is essential for reliable diagnoses and treatment planning. The patient's pose during radiography is one of the most important factors…
Convolutional Neural Networks Do Work with Pre-Defined Filters
Christoph Linse, Erhardt Barth, Thomas Martinetz
We present a novel class of Convolutional Neural Networks called Pre-defined Filter Convolutional Neural Networks (PFCNNs), where all nxn convolution kernels with n>1 are pre-defin…
Leaky ReLUs That Differ in Forward and Backward Pass Facilitate Activation Maximization in Deep Neural Networks
Christoph Linse, Erhardt Barth, Thomas Martinetz
Activation maximization (AM) strives to generate optimal input stimuli, revealing features that trigger high responses in trained deep neural networks. AM is an important method of…
Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes
Julius Martinetz, Christoph Linse, Thomas Martinetz
We investigate the learning dynamics of classifiers in scenarios where classes are separable or classifiers are over-parameterized. In both cases, Empirical Risk Minimization (ERM)…
Do highly over-parameterized neural networks generalize since bad solutions are rare?
Julius Martinetz, Thomas Martinetz
We study over-parameterized classifiers where Empirical Risk Minimization (ERM) for learning leads to zero training error. In these over-parameterized settings there are many globa…
Large Neural Networks Learning from Scratch with Very Few Data and without Explicit Regularization
Christoph Linse, Thomas Martinetz
Recent findings have shown that highly over-parameterized Neural Networks generalize without pretraining or explicit regularization. It is achieved with zero training error, i.e.,…
Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning
Hammam Alshazly, Christoph Linse, Erhardt Barth +1
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. To this end, we adopt advanced d…
Feature Products Yield Efficient Networks
Philipp Grüning, Thomas Martinetz, Erhardt Barth
We introduce Feature-Product networks (FP-nets) as a novel deep-network architecture based on a new building block inspired by principles of biological vision. For each input featu…
Solving Raven's Progressive Matrices with Multi-Layer Relation Networks
Marius Jahrens, Thomas Martinetz
Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine lea…
Multi-layer Relation Networks
Marius Jahrens, Thomas Martinetz
Relational Networks (RN) as introduced by Santoro et al. (2017) have demonstrated strong relational reasoning capabilities with a rather shallow architecture. Its single-layer desi…
Adaptive Hierarchical Sensing for the Efficient Sampling of Sparse and Compressible Signals
Henry Schütze, Erhardt Barth, Thomas Martinetz
We present the novel adaptive hierarchical sensing algorithm K-AHS, which samples sparse or compressible signals with a measurement complexity equal to that of Compressed Sensing (…
Deep Convolutional Neural Networks as Generic Feature Extractors
Lars Hertel, Erhardt Barth, Thomas Käster +1
Recognizing objects in natural images is an intricate problem involving multiple conflicting objectives. Deep convolutional neural networks, trained on large datasets, achieve conv…
Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks
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. We show that the…
Committees of deep feedforward networks trained with few data
Bogdan Miclut, Thomas Kaester, Thomas Martinetz +1
Deep convolutional neural networks are known to give good results on image classification tasks. In this paper we present a method to improve the classification result by combining…
The phase response of the cortical slow oscillation
Arne Weigenand, Thomas Martinetz, Jens Christian Claussen
Cortical slow oscillations occur in the mammalian brain during deep sleep and have been shown to contribute to memory consolidation, an effect that can be enhanced by electrical st…
On the boundedness of an iteration involving points on the hypersphere
Thomas Binder, Thomas Martinetz
For a finite set of points on the unit hypersphere in we consider the iteration , where is the point of farthest from . Restricti…