Related papers: From sample to knowledge: Towards an integrated ap…

Large annotated datasets are crucial for the success of deep neural networks, but labeling data can be prohibitively expensive in domains such as medical imaging. This work tackles the subset selection problem: selecting a small set of the…

The thesis explores the role machine learning methods play in creating intuitive computational models of neural processing. Combined with interpretability techniques, machine learning could replace human modeler and shift the focus of human…

Scientific knowledge develops through cumulative discoveries that build on, contradict, contextualize, or correct prior findings. Scientists and journalists often communicate these incremental findings to lay people through visualizations…

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…

Statistical shape modeling (SSM) has recently taken advantage of advances in deep learning to alleviate the need for a time-consuming and expert-driven workflow of anatomy segmentation, shape registration, and the optimization of…

Recent experimental advances in neuroscience have opened new vistas into the immense complexity of neuronal networks. This proliferation of data challenges us on two parallel fronts. First, how can we form adequate theoretical frameworks…

Motivation: Biological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. In the past years, feature learning methods that are…

Deep learning models have gained remarkable performance on a variety of image classification tasks. However, many models suffer from limited performance in clinical or medical settings when data are imbalanced. To address this challenge, we…

A central challenge in data visualization is to understand which data samples are required to generate an image of a data set in which the relevant information is encoded. In this work, we make a first step towards answering the question of…

In real-world clinical settings, data distributions evolve over time, with a continuous influx of new, limited disease cases. Therefore, class incremental learning is of great significance, i.e., deep learning models are required to learn…

Concept bottleneck models (CBMs), which predict human-interpretable concepts (e.g., nucleus shapes in cell images) before predicting the final output (e.g., cell type), provide insights into the decision-making processes of the model.…

This paper proposes a novel neuro-symbolic approach for sensor signal-based knowledge discovery, focusing on identifying latent subclasses in time series classification tasks. The approach leverages gradient-based saliency maps derived from…

New knowledge builds upon existing foundations, which means an interdependent relationship exists between knowledge, manifested in the historical development of the scientific system for hundreds of years. By leveraging natural language…

Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…

Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available. Previous methods require a lot of extra computational costs to update one or more generators and their…

The scientific literature is a rich source of information for data mining with conceptual knowledge graphs; the open science movement has enriched this literature with complementary source code that implements scientific models. To exploit…

We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach…

Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that can be interpreted in multiple ways, over-confidently…

Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated…

The major problem in information theoretic analysis of neural responses and other biological data is the reliable estimation of entropy--like quantities from small samples. We apply a recently introduced Bayesian entropy estimator to…