[Dec 17th 2018] Deep Graph Infomax

Pietro LiĆ² (University of Cambridge) Dec 17, 2018 – 2:30 PM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs—both […]

Read More »

[Dec 12th 2018] LabMeeting: How to extend GNNs: from changing the neuron model to transductive learning

Giorgio Ciano (DIISM, University of Siena) Dec 12, 2018 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Most of the techniques used in Machine Learning (e.g. Deep Neural Networks) use vectors as inputs. However, graphs are a data structure that is more general and suitable to represent real-world problems. Even if […]

Read More »

[Dec 12th 2018] Evolutionary Coresets and Machine Learning Epistemology

Pietro Barbiero (DISMA, Politecnico di Torino) Dec 12, 2018 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description In recent years, machine learning research has proposed effective algorithms, with huge impacts on applications ranging from medicine to autonomous driving cars. Although these models are powerful and accurate, they show serious weaknesses, such […]

Read More »

[Dec 12th 2018] Neural Biclustering in Gene Expression Analysis

Giansalvo Cirrincione (University of Picardie Jules Verne (UPJV), Amiens (France) and University of South Pacific (USP), Suva, Fiji) Dec 12, 2018 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Clustering in high dimensional spaces is a very difficult task. Dealing with DNA microarrays is even more difficult because gene subsets are […]

Read More »

[Dec 5th 2018] LabMeeting: Unity: A General Platform for Intelligent Agents

Luca Pasqualini (DIISM, University of Siena) Dec 5, 2018 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Recent advances in Deep Reinforcement Learning and Robotics have been driven by the presence of increasingly realistic and complex simulation environments. Many of the existing platforms, however, provide either unrealistic visuals, inaccurate physics, low […]

Read More »