Valentina Piras

Associato con Incarico di Collaborazione

Visual Computing (VC)

Stanza: C-19

Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo"
Area della Ricerca CNR di Pisa
Via G. Moruzzi 1
56124 PISA - Italy

email: Questo indirizzo email è protetto dagli spambots. È necessario abilitare JavaScript per vederlo.

Fax: +39 050 315 2040

Lista completa pubblicazioni: Clicca qui

In Evidenza

Seminari

Giovani in un'ora - Ciclo di seminari - Terza parte

16-10-2024

Gabriele Lagani - "Hebbian learning algorithms for deep neural networks: explorations and outlooks"Abstract: Deep learning systems have achieved outstanding results in various AI tasks. However, such system suffer from a number of limitations, for example in terms of energy an...

Room: C-29

Seminari

Giovani in un'ora - Ciclo di seminari - Seconda parte

09-10-2024

Saira Bano - "From Complexity to Clarity: Enhancing Cross-Modal Knowledge Distillation via Multimodal Teacher Ensembles"Abstract: Traditional knowledge distillation (KD) typically uses a large, complex teacher model, often trained to a single modality, to transfer knowledge to...

Room: C-29

Seminari

Patient Interaction – for well-being, productivity and sustainability

08-10-2024

We live in aworld of instant results and fleeting gratification. In HCI no less: the designprinciples for direct manipulation require immediate feedback and, in the caseof graphical actions, sub-second responses. In addition, computers expect us togive them our undivided atten...

Room: Aula Faedo C-29

Seminari

Giovani in un'ora - Ciclo di seminari - Prima parte

02-10-2024

Ali Reza Omrani - "Machine Learning to Measure Vocal Stereotypy: An Extension"Abstract: Repeated measurement of behavior is a process central to behavior analysis, but its implementation occasionally requires hiring observers dedicated exclusively to data collection, which may...

Room: C-29

Seminari

A general framework for distributed approximate similarity search with arbitrary distances

26-09-2024

While many similarity search algorithms are specifically adapted to metric distances,they are unsuitable for alternatives like the cosine distance, which has gained popularity, particularly with embeddings and text mining. To address thisissue, we propose GDASC (General Distri...

Room: C-29

Seminari

Model-Driven Engineering Meets Model-Based Testing

17-09-2024

In this talk, I will focus on a connection between stable-failures refinement and the ioco conformance relation. Both behavioural relations underlie methodologies that have gained traction in industry: stable-failures refinement is used in several commercial Model-Driven Engin...

Room: Faedo (C-29)

Seminari

Explainability in deep learning models applied to spatio-temporal problems

13-09-2024

Artificial Intelligence (AI) is transforming society, affecting everything from industry to decision making, and concerns about its transparency have increased. Explainable Artificial Intelligence (XAI) is crucial to address this problem, allowing to obtain a better understand...

Room: C-29

Seminari

Making 5G Networks Reliable for Next-generation Applications using AI

27-05-2024

The emergence of 5G technology marks a significant milestone in developing telecommunication networks, enabling exciting new applications such as augmented reality and self-driving vehicles. However, these improvements bring an increased management complexity and a special con...

Room: C-29

Seminari

Cargo Cult Architecture: An Empirical Investigation into the Maintainability Benefits of Design Patterns

24-05-2024

There have been many claims for the benefits of using patterns in software design and implementation. In this research we were interested to understand whether adopting patterns positively affects a project's long-term maintainability, as measured by its feature velocity and ...

Room: C-29

Seminari

Runtime Metaphors of Software Development Tools

24-04-2024

Software developers utilize a wide range of features in their integrated development environments, such as text search, documentation views, or inline hints in the editor. Many of these features traditionally operate only on static representations of programs, i.e., their sour...

Room: Aula Faedo - C-29