[May 31st 2018] LabMeeting: Depth growing neural networks

Vincenzo Laveglia (DIISM, University of Siena) May 31, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Being able to train neural networks (shallow or deep) requires the ability to identify the right hyper-parameters for the model. Some of these hyper-parameters are more related to the training procedure (epochs, learning rate, […]

Read More »

[May 24th 2018] LabMeeting: Geometric deep learning: dealing to structured data

Alberto Rossi (DIISM, University of Siena) May 24, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Many research areas deal with structured data, like social science, biology and computer graphics. Such geometric data could be very large and complex (social network), and machine learning techniques reveal their power to deal […]

Read More »

[May 28th 2018] Deep Learning of Barcode Sequences

Dr. Stefan C. Kremer, Professor (School of Computer and Science, University of Guelph, ON, CANADA) May 28, 2018 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Biological systems, on all scales, are essentially information processing and control systems. From this perspective, analogies between biological processes and computational processes can be drawn. […]

Read More »

[May 10th 2018] (Social) Network Analysis as a paradigm for knowledge extraction in various contexts

Domenico Ursino (Università Politecnica delle Marche) May 6, 2018 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description (Social) Network Analysis has been, and is currently, under investigation. Indeed, it is rooted in graph theory, has received a lot of attention from sociologists in the second half of the last century, and […]

Read More »

[May 10th 2018] LabMeeting: DBox: Deep Learning for Bounding Box Supervision in Semantic Segmentation

Simone Bonechi (DIISM, University of Siena) May 10, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Most of the leading convolutional neural networks for semantic segmentation exploit a large number of pixel–level annotations. Such human based labelling require a considerable effort that complicate the creation of large–scale datasets. In this […]

Read More »