How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
Thomas ist currently working at Technische Universität Berlin. Thomas does research in Statistics, Data Mining and Machine Learning. Thomas Goerttler worked at Hasso-Plattner Institute before. The former project was 'Missing value invariant data mining'.
It is common practice to reuse models initially trained on different data to increase downstream task performance. Especially in the computer vision domain, ImageNet-pretrained weights have been successfully used for various tasks. In this work, we investigate the impact of transfer learning for segmentation problems, being pixel-wise classificatio...
In transfer learning, only the last part of the networks - the so-called head - is often fine-tuned. Representation similarity analysis shows that the most significant change still occurs in the head even if all weights are updatable. However, recent results from few-shot learning have shown that representation change in the early layers, which are...
Real-time load information in public transport is of high importance for both passengers and service providers. Neural algorithms have shown a high performance on various object counting tasks and play a continually growing methodological role in developing automated passenger counting systems. However, the publication of public-space video footage...
In this article, we give an interactive introduction to model-agnostic meta-learning (MAML), a well-establish method in the area of meta-learning. Meta-learning is a research field that attempts to equip conventional machine learning architectures with the power to gain meta-knowledge about a range of tasks to solve problems like the one above on a...
In past years model-agnostic meta-learning (MAML) has been one of the most promising approaches in meta-learning. It can be applied to different kinds of problems, e.g., reinforcement learning, but also shows good results on few-shot learning tasks. Besides their tremendous success in these tasks, it has still not been fully revealed yet, why it wo...
In past years model-agnostic meta-learning (MAML) has been one of the most promising approaches in meta-learning. It can be applied to different kinds of problems, e.g., reinforcement learning, but also shows good results on few-shot learning tasks. Besides their tremendous success in these tasks, it has still not been fully revealed yet, why it w...
Generative adversarial nets (GANs) have shown their potential in various tasks like image generation, 3D object generation, image super-resolution, and video prediction. Nevertheless, they are still considered as highly unstable to train and are endangered to miss modes. One problem is that real data is usually discontinuous, whereas the prior dist...
Quantify Deep Networks - Towards Understanding of Transferable Representations We want to understand why deep networks learn and are transferable
Traditional data mining techniques cannot be applied on incomplete datasets without requiring data imputation. The goal of the project is to adapt and develop new data mining algorithm which are invariant to missing data.