VI-SFI Workshop on uncertainty
Workshop for VI consortium
This workshop aims to bring together both academic researchers and industrial practitioners to share visions on the explainable artificial intelligence (XAI), and the practical usages in different AI applications, such as biomedical images and marine science.
In this workshop, we have invited speakers that will give some insight both in classifier calibration as well as in Bayesian deep learning, to shed light on one of the main research challenges in Visual Intelligence, namely Confidence and Uncertainty.
Machine learning methods, such as deep neural networks, have been shown to be very successful for prediction in many different applications. Standard use of such methods do however not account for or underestimate the full uncertainty related to these predictions. The Bayesian approach allows for a formal way of making proper uncertainty quantification. Recently, such methods have also gained popularity within the machine learning community. In this talk Professor Geir Olve Storvik from UiO will describe how the Bayesian methodology can be applied to machine learning.We will discuss both advantages and challenges related to apply such methods in practice.
Bayesian Neural Networks are an alternative approach to classic NN models, offering "built-in" uncertainty measures and convenient regularization. Performing inference on a BNN results in a joint posterior distribution of network parameters, which can provide insight into what makes for a well-specified network for a given problem. Master student at UiT, Jonathan Edward Berezowski, discusses how to define a BNN with these features and introduce the method of Reversible Jump Markov Chain Monte Carlo as one potential approach to inference.
The research area of probability calibration refers to a set of work that focuses on the uncertainty and confidence of model predictions. On the top level, we want the models to be well-calibrated on the predicted probabilities. That is, the target variable should follow closely to the distribution as indicated by every distinct prediction. In this talk, Research Associate Hao Song from University of Bristol will provide an overview of the research area, including typical definitions, evaluation measures, and approaches that can improve the level of calibration.
This VI workshop aims to start the development of best practices of data management to streamline and prevent common pitfalls by sharing challenges and solutions related to the handling of medical data for machine learning research.
A Visual Intelligence workshop that covers approaches to achieve learning from limited data.
Benjamin Kellenberger from EPFL presents his work with limited training data in applications of unmanned aerial vehicles in earth observation to monitor wildlife. He presented his work "When a Few Clicks Make All the Difference: Improving Weakly-supervised Wildlife Detection in UAV Images", on the first Visual Intelligence Workshop on Limited training data.
Obtaining fully labeled datasets suitable for machine learning can be expensive, time-consuming, and impractical in many fields, limiting the applicability of the commonly used supervised approaches. Alba Ordoñes from NR presents their work with limited training data in the marine domain.