Search Results for author:
Found 14 papers, 7 papers with code
Overlooked Data in Typological Databases: What Grambank Teaches Us About Gaps in Grammars
We then aggregate these comments and the coded values to derive a level of description for 17 grammatical domains that Grambank covers (negation, adnominal modification, participant marking, tense, aspect, etc.).
Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries
Sparse regularization techniques are well-established in machine learning, yet their application in neural networks remains challenging due to the non-differentiability of penalties like the $L_1$ norm, which is incompatible with stochastic gradient descent.
Linearization Turns Neural Operators into Function-Valued Gaussian Processes
We introduce LUNO, a novel framework for approximate Bayesian uncertainty quantification in trained neural operators.
Generalizing Orthogonalization for Models with Non-Linearities
The complexity of black-box algorithms can lead to various challenges, including the introduction of biases.
Post-Training Network Compression for 3D Medical Image Segmentation: Reducing Computational Efforts via Tucker Decomposition
The application of Tucker decomposition to the TS model substantially reduced the model parameters and FLOPs across various compression rates, with limited loss in segmentation accuracy.
Post-hoc Orthogonalization for Mitigation of Protected Feature Bias in CXR Embeddings
Methods: An orthogonalization is utilized to remove the influence of protected features (e. g., age, sex, race) in CXR embeddings, ensuring feature-independent results.
Adversarial Anomaly Detection using Gaussian Priors and Nonlinear Anomaly Scores
Anomaly detection in imbalanced datasets is a frequent and crucial problem, especially in the medical domain where retrieving and labeling irregularities is often expensive.
Constrained Probabilistic Mask Learning for Task-specific Undersampled MRI Reconstruction
Undersampling is a common method in Magnetic Resonance Imaging (MRI) to subsample the number of data points in k-space, reducing acquisition times at the cost of decreased image quality.
Automated wildlife image classification: An active learning tool for ecological applications
(2) We provide an active learning (AL) system that allows training deep learning models very efficiently in terms of required human-labeled training images.
Cascaded Latent Diffusion Models for High-Resolution Chest X-ray Synthesis
While recent advances in large-scale foundational models show promising results, their application to the medical domain has not yet been explored in detail.
ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports
In a questionnaire, we asked 15 radiologists to assess the quality of radiology reports simplified by ChatGPT.
Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation
The application of deep learning in survival analysis (SA) allows utilizing unstructured and high-dimensional data types uncommon in traditional survival methods.
Survival-oriented embeddings for improving accessibility to complex data structures
We propose a hazard-regularized variational autoencoder that supports straightforward interpretation of deep neural architectures in the context of survival analysis, a field highly relevant in healthcare.
Using Supervised Learning to Classify Metadata of Research Data by Discipline of Research
Both applications perform at scale with the proposed models which are available for re-use.
