12 citations · 28 across the 26 of their papers we have counts for
27 papers
Uncertainty Identifies Difficult Samples Across Methods: A Multi-Task Study on a Heterogeneous Skin Lesion Dataset
Leon Koole, Jiapan Guo, Matias Valdenegro-Toro
Skin lesion classifiers can be confidently wrong on the cases that matter most, so knowing when a prediction should not be trusted is clinically as useful as the prediction. We stu…
YieldSAT: A Multimodal Benchmark Dataset for High-Resolution Crop Yield Prediction
Miro Miranda, Deepak Pathak, Patrick Helber +10
Crop yield prediction requires substantial data to train scalable models. However, creating yield prediction datasets is constrained by high acquisition costs, heterogeneous data q…
Informed Learning for Estimating Drought Stress at Fine-Scale Resolution Enables Accurate Yield Prediction
Miro Miranda, Marcela Charfuelan, Matias Valdenegro Toro +1
Water is essential for agricultural productivity. Assessing water shortages and reduced yield potential is a critical factor in decision-making for ensuring agricultural productivi…
Forecasting Smog Clouds With Deep Learning
Valentijn Oldenburg, Juan Cardenas-Cartagena, Matias Valdenegro-Toro
In this proof-of-concept study, we conduct multivariate timeseries forecasting for the concentrations of nitrogen dioxide (NO2), ozone (O3), and (fine) particulate matter (PM10 & P…
The Dilemma of Uncertainty Estimation for General Purpose AI in the EU AI Act
Matias Valdenegro-Toro, Radina Stoykova
The AI act is the European Union-wide regulation of AI systems. It includes specific provisions for general-purpose AI models which however need to be further interpreted in terms…
Measuring Orthogonality as the Blind-Spot of Uncertainty Disentanglement
Ivo Pascal de Jong, Andreea Ioana Sburlea, Matthia Sabatelli +1
Aleatoric (data) and epistemic (knowledge) uncertainty are textbook components of Uncertainty Quantification. Jointly estimating these components has been shown to be problematic a…
Terrain Classification Enhanced with Uncertainty for Space Exploration Robots from Proprioceptive Data
Mariela De Lucas Álvarez, Jichen Guo, Raul Domínguez +1
Terrain Classification is an essential task in space exploration, where unpredictable environments are difficult to observe using only exteroceptive sensors such as vision. Impleme…
Sanity Checks for Explanation Uncertainty
Matias Valdenegro-Toro, Mihir Mulye
Explanations for machine learning models can be hard to interpret or be wrong. Combining an explanation method with an uncertainty estimation method produces explanation uncertaint…
Transferring BCI models from calibration to control: Observing shifts in EEG features
Ivo Pascal de Jong, Lüke Luna van den Wittenboer, Matias Valdenegro-Toro +1
Public Motor Imagery-based brain-computer interface (BCI) datasets are being used to develop increasingly good classifiers. However, they usually follow discrete paradigms where pa…
Uncertainty Quantification for cross-subject Motor Imagery classification
Prithviraj Manivannan, Ivo Pascal de Jong, Matias Valdenegro-Toro +1
Uncertainty Quantification aims to determine when the prediction from a Machine Learning model is likely to be wrong. Computer Vision research has explored methods for determining…
Uncertainty Quantification for Gradient-based Explanations in Neural Networks
Mihir Mulye, Matias Valdenegro-Toro
Explanation methods help understand the reasons for a model's prediction. These methods are increasingly involved in model debugging, performance optimization, and gaining insights…
Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review
Ivo Pascal de Jong, Andreea Ioana Sburlea, Matias Valdenegro-Toro
Purpose: Uncertainty Quantification (UQ) has gained traction in an attempt to improve the interpretability and robustness of machine learning predictions. Specifically (medical) bi…
ChatGPT Prompting Cannot Estimate Predictive Uncertainty in High-Resource Languages
Martino Pelucchi, Matias Valdenegro-Toro
ChatGPT took the world by storm for its impressive abilities. Due to its release without documentation, scientists immediately attempted to identify its limits, mainly through its…
Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models
Kumud Lakara, Matias Valdenegro-Toro
Trusting the predictions of deep learning models in safety critical settings such as the medical domain is still not a viable option. Distentangled uncertainty quantification in th…
A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation
Lokesh Veeramacheneni, Matias Valdenegro-Toro
Safety-critical applications like autonomous driving use Deep Neural Networks (DNNs) for object detection and segmentation. The DNNs fail to predict when they observe an Out-of-Dis…
Feature Disentanglement of Robot Trajectories
Matias Valdenegro-Toro, Daniel Harnack, Hendrik Wöhrle
Modeling trajectories generated by robot joints is complex and required for high level activities like trajectory generation, clustering, and classification. Disentagled representa…
Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning
Aaqib Parvez Mohammed, Matias Valdenegro-Toro
Reinforcement Learning (RL) based solutions are being adopted in a variety of domains including robotics, health care and industrial automation. Most focus is given to when these s…
Exploring the Limits of Epistemic Uncertainty Quantification in Low-Shot Settings
Matias Valdenegro-Toro
Uncertainty quantification in neural network promises to increase safety of AI systems, but it is not clear how performance might vary with the training set size. In this paper we…
Teaching Uncertainty Quantification in Machine Learning through Use Cases
Matias Valdenegro-Toro
Uncertainty in machine learning is not generally taught as general knowledge in Machine Learning course curricula. In this paper we propose a short curriculum for a course about un…
Can Reinforcement Learning for Continuous Control Generalize Across Physics Engines?
Aaqib Parvez Mohammed, Matias Valdenegro-Toro
Reinforcement learning (RL) algorithms should learn as much as possible about the environment but not the properties of the physics engines that generate the environment. There are…
Know Where To Drop Your Weights: Towards Faster Uncertainty Estimation
Akshatha Kamath, Dwaraknath Gnaneshwar, Matias Valdenegro-Toro
Estimating epistemic uncertainty of models used in low-latency applications and Out-Of-Distribution samples detection is a challenge due to the computationally demanding nature of…
Hey Human, If your Facial Emotions are Uncertain, You Should Use Bayesian Neural Networks!
Maryam Matin, Matias Valdenegro-Toro
Facial emotion recognition is the task to classify human emotions in face images. It is a difficult task due to high aleatoric uncertainty and visual ambiguity. A large part of the…
Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification
Matias Valdenegro-Toro
Fast estimates of model uncertainty are required for many robust robotics applications. Deep Ensembles provides state of the art uncertainty without requiring Bayesian methods, but…
Results from the Robocademy ITN: Autonomy, Disturbance Rejection and Perception for Advanced Marine Robotics
Matias Valdenegro-Toro, Mariela De Lucas Alvarez, Mariia Dmitrieva +7
Marine and Underwater resources are important part of the economy of many countries. This requires significant financial resources into their construction and maintentance. Robotic…