| 2026 | COMPSAC | KiMeKo: A Collaborative AI Platform for Medical Device Development. | Serge Autexier, Nihat Ay, Stefan Fischer, Lars Kaderali, Thomas Kirste, Martin Leucker, Christoph Lth, Thomas Martinetz, Philipp Rostalski, Alexander Schlaefer, Frank ckert |
| 2026 | ESANN | Local Concept Embeddings in the Context of Self-Supervised Learning. | Kim Paulke, Hans-Oliver Hansen, Thomas Martinetz, Gesina Schwalbe |
| 2026 | ICPR | Nearest-Neighbor Density Estimation for Dependency Suppression. | Kathleen Anderson, Thomas Martinetz |
| 2025 | ESANN | Deciphering Barlow Twins: Reduncy Reduction is Insufficient and Normalization is Key. | Hans-Oliver Hansen, Marius Jahrens, Thomas Martinetz |
| 2025 | ESANN | Investigating the Impact of Imbalanced Medical Data on the Performance of Self-Supervised Learning Approaches. | Manuel Laufer, Felicitas Brokmann, Dominik Mairhfer, Erhardt Barth, Thomas Martinetz |
| 2024 | ESANN | AI-based Collimation Optimization for X-Ray Imaging using Time-of-Flight Cameras. | Dominik Mairhfer, Manuel Laufer, Lennart Berkel, Arpad Bischof, Erhardt Barth, Jrg Barkhausen, Thomas Martinetz |
| 2024 | ICANN | Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations. | Kathleen Anderson, Thomas Martinetz |
| 2024 | ICANN | Enhancing Generalization in Convolutional Neural Networks Through Regularization with Edge and Line Features. | Christoph Linse, Beatrice Brckner, Thomas Martinetz |
| 2024 | IJCNN | Leaky ReLUs That Differ in Forward and Backward Pass Facilitate Activation Maximization in Deep Neural Networks. | Christoph Linse, Erhardt Barth, Thomas Martinetz |
| 2024 | IJCNN | Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes. | Julius Martinetz, Christoph Linse, Thomas Martinetz |
| 2023 | ICANN | Population Coding Can Greatly Improve Performance of Neural Networks: A Comparison. | Marius Jahrens, Hans-Oliver Hansen, Rebecca Khler, Thomas Martinetz |
| 2023 | IJCNN | Convolutional Neural Networks Do Work with Pre-Defined Filters. | Christoph Linse, Erhardt Barth, Thomas Martinetz |
| 2020 | ICANN | Log-Nets: Logarithmic Feature-Product Layers Yield More Compact Networks. | Philipp Grning, Thomas Martinetz, Erhardt Barth |
| 2020 | IJCNN | Solving Raven's Progressive Matrices with Multi-Layer Relation Networks. | Marius Jahrens, Thomas Martinetz |
| 2017 | ACIVS | Sensing Forest for Pattern Recognition. | Irina Burciu, Thomas Martinetz, Erhardt Barth |
| 2017 | IJCNN | Recursive autoconvolution for unsupervised learning of convolutional neural networks. | Boris Knyazev, Erhardt Barth, Thomas Martinetz |
| 2017 | IJCNN | Perception space analysis: From color vision to odor perception. | Amir Madany Mamlouk, Martin Haker, Thomas Martinetz |
| 2015 | IJCNN | Deep convolutional neural networks as generic feature extractors. | Lars Hertel, Erhardt Barth, Thomas Kster, Thomas Martinetz |
| 2015 | IJCNN | Learning orthogonal sparse representations by using geodesic flow optimization. | Henry Schtze, Erhardt Barth, Thomas Martinetz |
| 2014 | ESANN | Learning and modeling big data. | Barbara Hammer, Haibo He, Thomas Martinetz |
| 2014 | ICANN | Global Metric Learning by Gradient Descent. | Jens Hocke, Thomas Martinetz |
| 2013 | ICANN | Feature Weighting by Maximum Distance Minimization. | Jens Hocke, Thomas Martinetz |
| 2012 | ICANN | A Multivariate Approach to Estimate Complexity of FMRI Time Series. | Henry Schtze, Thomas Martinetz, Silke Anders, Amir Madany Mamlouk |
| 2011 | ICANN | On the Problem of Finding the Least Number of Features by L1-Norm Minimisation. | Sascha Klement, Thomas Martinetz |
| 2010 | ESANN | Learning sparse codes for image reconstruction. | Kai Labusch, Thomas Martinetz |
| 2010 | ICANN | The Support Feature Machine for Classifying with the Least Number of Features. | Sascha Klement, Thomas Martinetz |
| 2010 | ICANN | A Learned Saliency Predictor for Dynamic Natural Scenes. | Eleonora Vig, Michael Dorr, Thomas Martinetz, Erhardt Barth |
| 2010 | ICMLA | A New Approach to Classification with the Least Number of Features. | Sascha Klement, Thomas Martinetz |
| 2010 | ICPR | Statistical Fourier Descriptors for Defect Image Classification. | Fabian Timm, Thomas Martinetz |
| 2009 | ICANN | Multimodal Sparse Features for Object Detection. | Martin Haker, Thomas Martinetz, Erhardt Barth |
| 2008 | CVPR | Shading constraint improves accuracy of time-of-flight measurements. | Martin Bhme, Martin Haker, Thomas Martinetz, Erhardt Barth |
| 2008 | CVPR | Scale-invariant range features for time-of-flight camera applications. | Martin Haker, Martin Bhme, Thomas Martinetz, Erhardt Barth |
| 2008 | ESANN | Learning Data Representations with Sparse Coding Neural Gas. | Kai Labusch, Erhardt Barth, Thomas Martinetz |
| 2008 | ETRA | A software framework for simulating eye trackers. | Martin Bhme, Michael Dorr, Mathis Graw, Thomas Martinetz, Erhardt Barth |
| 2008 | ICANN | Reliability of Cross-Validation for SVMs in High-Dimensional, Low Sample Size Scenarios. | Sascha Klement, Amir Madany Mamlouk, Thomas Martinetz |
| 2008 | ICANN | Sparse Coding Neural Gas for the Separation of Noisy Overcomplete Sources. | Kai Labusch, Erhardt Barth, Thomas Martinetz |
| 2008 | ICPR | Fast model selection for MaxMinOver-based training of support vector machines. | Fabian Timm, Sascha Klement, Thomas Martinetz |
| 2008 | IJCNN | Uncertainty propagation for quality assurance in Reinforcement Learning. | Daniel Schneega, Steffen Udluft, Thomas Martinetz |
| 2007 | ESANN | The Intrinsic Recurrent Support Vector Machine. | Daniel Schneega, Anton Maximilian Schfer, Thomas Martinetz |
| 2007 | ESANN | Neural Rewards Regression for near-optimal policy identification in Markovian and partial observable environments. | Daniel Schneega, Steffen Udluft, Thomas Martinetz |
| 2007 | ESANN | Explicit Kernel Rewards Regression for data-efficient near-optimal policy identification. | Daniel Schneega, Steffen Udluft, Thomas Martinetz |
| 2007 | ICANN | Improving Optimality of Neural Rewards Regression for Data-Efficient Batch Near-Optimal Policy Identification. | Daniel Schneega, Steffen Udluft, Thomas Martinetz |
| 2006 | ESANN | OnlineDoubleMaxMinOver: a simple approximate time and information efficient online Support Vector Classification method. | Daniel Schneega, Thomas Martinetz, Michael Clausohm |
| 2006 | ETRA | Gaze-contingent temporal filtering of video. | Martin Bhme, Michael Dorr, Thomas Martinetz, Erhardt Barth |
| 2006 | ICANN | MaxMinOver Regression: A Simple Incremental Approach for Support Vector Function Approximation. | Daniel Schneega, Kai Labusch, Thomas Martinetz |
| 2005 | ICANN | SoftDoubleMinOver: A Simple Procedure for Maximum Margin Classification. | Thomas Martinetz, Kai Labusch, Daniel Schneega |
| 2004 | GI | Saliency Extraction for Gaze-Contingent Displays. | Martin Bhme, Christopher Krause, Thomas Martinetz, Erhardt Barth |
| 2004 | IJCNN | MaxMinOver: a simple incremental learning procedure for support vector classification. | Thomas Martinetz |
| 2003 | ESANN | Model-Free Functional MRI Analysis Using Topographic Independent Component Analysis. | Anke Meyer-Bse, Thomas D. Otto, Thomas Martinetz, Dorothee Auer, Axel Wismller |
| 2003 | IJCNN | Statistical learning for detecting protein-DNA-binding sites. | Thomas Martinetz, Jan E. Gewehr, Jan T. Kim |
| 2001 | RoboCup | A Method for Incorporation of New Evidence to Improve World State Estimation. | Martin Haker, Andr Meyer, Daniel Polani, Thomas Martinetz |
| 2000 | RoboCup | Team Description for Lucky Lbeck - Evidence-Based World State Estimation. | Daniel Polani, Thomas Martinetz |
| 1991 | WI | Vector Quantization Algorithm for Time Series Prediction and Visuo-Motor Control of Robots. | Stan Berkovitch, Philippe Dalger, Ted Hesselroth, Thomas Martinetz, Benot Nol, Jrg A. Walter, Klaus Schulten |
| 1990 | IJCNN | Hierarchical neural net for learning control of a robot's arm and gripper. | Thomas Martinetz, Klaus Schulten |