Welcome!

This is the official web site of Siena Artificial Intelligence Laboratory. The focus of our research is on machine learning. In the last few years, we’ve been mainly involved in the conception of new theories of learning in structured domains and in their applications to pattern recognition and mining the web. We are also interested […]

Read More »

A Variational Framework for Laws of Learning

Simplicity and elegance have always been incredibly useful criteria for the development of successful theories that describe natural phenomena. Variational methods frame this parsimony principles into precise mathematical statements. In this thesis we showed how we can formulate learning theories using calculus of variations. Despite the natural way in which learning problem can be formulated […]

Read More »

[Mar 4th 2020] LabMeeting: Human-Driven FOL Explanations of Deep Learning

Gabriele Ciravegna (University of Florence) Mar 4, 2020 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Deep neural networks are usually considered black-boxes due to their complex internal architecture, that cannot straightforwardly provide human-understandable explanations on how they behave. Indeed, Deep Learning is still viewed with skepticism in those real-world domains […]

Read More »

On the Integration of Logic and Learning

Giannini’s thesis A key point in the success of machine learning, and in particular deep learning, has been the availability of high-performance computing architectures allowing to process a large amount of data. However, this potentially prevents a wider application of machine learning in real world applications, where the collection of training data is often a […]

Read More »

[Feb 19th 2020] LabMeeting: Embedding of FRPN in CNN architecture

Alberto Rossi (University of Florence) Feb 19, 2020 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description This paper extends the fully recursive perceptron network (FRPN) model for vectorial inputs to include deep convolutional neural networks (CNNs) which can accept multi-dimensional inputs. A FRPN consists of a recursive layer, which, given a […]

Read More »

[Feb 19th 2020] LabMeeting: The Latent Topic Block Model for the Co-Clustering of Textual Interaction Data

Marco Corneli Feb 19, 2020 – 11:45 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description We consider textual interaction data involving two disjoint sets of individuals/objects. An example of such data is given by the reviews on web platforms (e.g. Amazon, TripAdvisor, etc.) where buyers comment on products/services they bought. We develop a […]

Read More »

[Feb 12th 2020] Creating a Commonsense Knowledge Base about Objects

Valerio Basile (University of Turin) Feb 12, 2020 – 11:40 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Today’s Web represents a huge repository of human knowledge, not only about facts, people, places and so on (encyclopedic knowledge), but also about everyday beliefs that average human beings are expected to hold (commonsense knowledge). […]

Read More »

[Feb 5th 2020] LabMeeting: Line-Based Automatic Sketches

Lisa Graziani (University of Florence) Feb 5, 2020 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Sketch generation from photos can be seen as a classic task of image to image translation with GANs. But in our work the sketch generation is addressed as an unsupervised problem based on a vectorial […]

Read More »

[Jan 29th 2020] LabMeeting: Learning in Text Streams, Discovery and Disambiguation of Entity and Relation Instances

Andrea Zugarini (University of Florence) Jan 29, 2020 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description We consider a scenario where an artificial agent is reading a stream of text composed of a set of narrations, and it is informed about the identity of some of the individuals that are mentioned […]

Read More »

[Jan 22nd 2020] LabMeeting: Analyzing and Improving the Image Quality of StyleGAN

Giorgio Ciano (University of Siena) Jan 22, 2020 – 11:00 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generativeimage modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. […]

Read More »