[Sep 23rd 2020] LabMeeting: Evaluating the impact of semantic features and domain knowledge on text categorization

Marco Ernandes Sep 23, 2020 – 11:45 – 12:30 AM Conference Meeting Description The text-mining field is currently in the eye of a technological storm: dozens of novel (and effective!) algorithms and architectures have been recently released, mainly by global AI players, such as Google, OpenAI, Microsoft. From a methodological point of view we observe […]

Read More »

[Sep 23th 2020] LabMeeting: Spectral Clustering with Graph Neural Networks for Graph Pooling

Niccolò Pancino (University of Florence) Sep 23, 2020 – 11:00 – 11:45 AM Conference Meeting Description Spectral clustering (SC) is a popular clustering technique to find strongly connected communities on a graph. It can be used in Graph Neural Networks to implement pooling operations that aggregate nodes belonging to the same cluster. However, SC is […]

Read More »

[Sep 16th 2020] LabMeeting: SAILenv: Learning in Virtual Visual Environments Made Simple

Enrico Meloni (University of Florence) Sep 16, 2020 – 11:00 AM Conference Meeting Description Recently, researchers in Machine Learning algorithms, Computer Vision scientists, engineers, and others, showed a growing interest in 3D simulators as a mean to artificially create experimental settings that are remarkably close to those in the real world. However, most of the […]

Read More »

[Jul 22nd 2020] LabMeeting: Partial Distance Correlation for Exploring Dependence Between Similarity Networks

Federica Baccini (University of Florence) Jul 22, 2020 – 11:00 AM Conference Meeting Description Similarity network fusion is a tool that aggregates the information coming from a multiplex network into a unique layer through a cross diffusion process. However, the process itself does not allow to infer which layer has the major impact in the […]

Read More »

[Jul 15th 2020] LabMeeting: Can Domain Knowledge Alleviate Adversarial Attacks in Multi-Label Classifiers?

Gabriele Ciravegna (University of Florence) Jul 15, 2020 – 11:00 AM Conference Meeting Description Adversarial attacks on machine learning-based classifiers, along with defence mechanisms, have been widely studied in the context of single-label classification problems. In this paper, we shift the attention to multi-label classification, where the availability of domain knowledge on the relationships among […]

Read More »

[July 1st 2020] LabMeeting: Next Segment Prediction

Lisa Graziani (University of Florence) Jul 1, 2020 – 11:00 AM Conference Meeting Description In general sketches are generated using generative adversarial models. We propose a new approach which represents the sketches as sequences of segments. This means that segments are ordered with respect to time, so we organize them considering a predefi ned criterion. We […]

Read More »

[Jun 24th 2020] LabMeeting: mCSM-membrane: predicting the effects of mutations on transmembrane proteins

Anna Visibelli (University of Siena) Jun 24, 2020 – 11:00 AM Conference Meeting Description Significant efforts have been invested into understanding and predicting the molecular consequences of mutations in protein coding regions, however nearly all approaches have been developed using globular, soluble proteins. These methods have been shown to poorly translate to studying the effects […]

Read More »

[Jun 17th 2020] LabMeeting: Analyzing and Improving the Image Quality of StyleGAN

Giorgio Ciano (University of Florence) Jun 17, 2020 – 11:00 AM Conference Meeting Description The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign generator […]

Read More »

[Jun 3rd 2020] LabMeeting: Wave Propagation of Visual Stimuli in Focus of Attention

Lapo Faggi (University of Florence) Jun 3, 2020 – 11:00 AM Conference Meeting Description Fast reactions to changes in the surrounding visual environment require efficient attention mechanisms to reallocate computational resources to the most relevant locations in the visual field. While current computational models keep improving their predictive ability thanks to the increasing availability of […]

Read More »