[Apr 3rd 2019]: Meaningful Explanations of Black Box AI Decision Systems

Dino Pedreschi (DIISM, University of Pisa) Apr 3, 2019 – 15:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Black box AI systems for automated decision making, often based on machine learning over (big) data, map a user’s features into a class or a score without exposing the reasons why. This is problematic […]

Read More »

[Apr 3rd 2019] LabMeeting: Learning Scene Decomposition and Visual Graph Representation

Matteo Tiezzi (DIISM, University of Siena) Apr 3, 2019 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description The ability to decompose visual scenes in terms of abstract building blocks is crucial for general intelligence. These basic building blocks are capable to represent meaningful properties, interactions and other relations across scenes. The […]

Read More »

[Mar 28th 2019]: Jumping Finite Automata

Prof. Alexander Meduna is a theoretical computer scientist and expert on compiler design, formal languages and automata. He is a professor of Computer Science at the Brno University of Technology. Mar 28, 2019 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description This talk proposes a new investigation area in automata theory […]

Read More »

[Mar 20th 2019] Lab Meeting: Towards laws of visual attention

Dario Zanca (DIISM, University of Siena) Mar 20, 2019 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description When eye-tracking devices are not a viable option, models of visual attention can be used to predict locations fixated by humans. We argue that the idea of a saliency map is ill-posed, and present […]

Read More »

[Mar 13th 2019] Lab Meeting: Integrating Learning and Reasoning with Deep Logic Models

Francesco Giannini (DIISM, University of Siena) Mar 13, 2019 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns. Probabilistic logic reasoning, on the other hand, is capable to take consistent and […]

Read More »

[Mar 6th 2019] LabMeeting: A Deep Learning Models Comparison for Brain Age Estimation

Simone Bonechi (DIISM, University of Siena) Mar 6, 2019 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description In recent years, deep learning and Convolutional Neural Networks (CNNs) have produced a devastating impact on computer vision, achieving outstanding results on a variety of problems, including medical image analysis. Recently, these techniques have […]

Read More »

[Feb 27th 2019] LabMeeting: Supervision Generation for Scene Text Segmentation with Multiscale Attention Networks

Paolo Andreini (DIISM, University of Siena) Feb 27, 2019 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description In this seminar, a novel approach to scene text segmentation is presented. The method exploits a new convolutional neural network model, called Segmentation Multiscale Attention Network (SMANet). Employing the SMANet the COCO–Text–Segmentation (COCO TS) […]

Read More »

[Feb 20th 2019] Increasing machine autonomy and ethics

Guglielmo Tamburrini, Università di Napoli Federico II. Feb 20, 2019 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description The rise of increasingly autonomous AI and robotic systems is bringing about a variety of novel and impending ethical issues. These include the issue whether certain forms of machine autonomy are morally admissible, […]

Read More »

[Feb 20th 2019] Explaining the behavior of learning classification systems: a model agnostic approach

Roberto Prevete, Università di Napoli Federico II. Feb 20, 2019 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description It is difficult to reconstruct and exhaustively explain the decisions/behaviors of current autonomous or semi-autonomous systems based on Machine Learning techniques. This characteristic is due to the fact that they usually do not […]

Read More »