Seminars

Abstract: A calibrated machine learning model produces probabilistic predictions that are well-aligned with real probabilities: it tends to be more certain when it is correct. Unfortunately, the unique characteristics of modern neural networks, e.g. over-parametrization or iterative training dynamics, can often result in overfitting the training data and generating over-confident predictions. The goal of this … Read more

We are pleased to present the Quantum Machine Learning Group (QML-CVC) on Friday, October 20, 2023. We will introduce the people and the main lines of work of the QML-CVC Group, discussing fundamental components and scientific challenges of the Quantum Machine Learning field while identifying potential applications in Computer Vision. The event will start with … Read more

Abstract: While machine learning models are continually improving, for most tasks they fail to achieve perfect predictive performance. In order to be a valuable tool in decision-making under uncertainty, it stands to reason that we want some statistical guarantees on the quality of probabilistic predictive models. Research into calibration regained popularity after repeated empirical observations … Read more

Abstract: In this talk, Dr Andrew D. Bagdanov, Dr Massimo Iuliani, Dr Dasara Shullani, Dr Daniele Baracchi & Simone Magistri will present the results of the research activity on multimedia content security carried out at the Information Engineering Department (DINFO) at the University of Florence. First, we will give a short introduction to the three … Read more

Abstract: Developing clinical predictive models by processing medical radiology images is often challenging due to high variability of data, noise and data scarcity. Using pre-trained feature extractors in deep learning configurations to initialise weights is often beneficial to the model optimisation process, leading to faster convergence and more accurate models. Although one can also benefit … Read more