Uncertainty in probabilistic classifiers predictions is a key concern when models are used to support human decision making, in broader probabilistic pipelines or when sensitive automatic decisions have to be taken.
Studies have shown that most models are not intrinsically well calibrated, meaning that their decision scores are not consistent.
We propose a framework using contrastive learning as a pre-training task to perform image classification in the presence of noisy labels. Recent strategies, such as pseudo-labelling, sample selection with Gaussian Mixture models, and weighted supervised contrastive learning have been combined into a fine-tuning phase following the pre-training.
Continue readingThis paper explains our participation in task 1of the CASE 2021 shared task. This task is about multilingual event extraction from the news. We focused on sub-task 4, event information extraction. This sub-task has a small training dataset, and we fine-tuned a multilingual BERT to solve this sub-task.
Continue readingThe General Data Protection Regulation (GDPR) requires data controllers to implement end-to-end compliance. Controllers must therefore ensure that the terms agreed with the data subject and their own obligations under GDPR are respected in the data flows from data subject to controllers, processors and sub-processors (i.e. data supply chain).
Continue readingThe assessment of the digital transformation progress is essential to understand and undertake in order to evaluate the level of maturity of data-driven companies in terms of data capabilities and to plan for improvement actions.
Continue readingMaturity models are helpful business tools that refine and develop how organizations conduct their businesses and benchmark their maturity status against a scale or with industry peers. They serve to prioritize the actions for improvement better and control the progress in reaching the target maturity stage.
Continue readingIn this paper, we propose a framework for image classification tasks, named MIC, that takes as input multi-view images, such as RGB-T images for surveillance purposes. We combine auto-encoder and generative adversarial network architectures to ensure the multi-view embedding in a common latent space.
Continue readingFor safety-critical systems involving AI components (such as in planes, cars, or healthcare), safety and associated certification tasks are one of the main challenges, which can become costly and difficult to address.
One key aspect is to ensure that the decisions a machine-learning classifier makes are properly calibrated.
Continue readingMolecular pathway databases represent cellular processes in a structured and standardized way. These databases support the community-wide utilization of pathway information in biological research and the computational analysis of high-throughput biochemical data. We present Padhoc, a pipeline for pathway ad hoc reconstruction.
Continue readingRadiomics is the main approach used to develop predictive models based on 3D Positron Emission Tomography (PET) scans of patients suffering from cancer. We propose a deep learning architecture associating a 2D feature extractor to a 3D CNN predictor.
Continue reading