Milano, Lombardia, Italia
Informazioni di contatto
980 follower
Oltre 500 collegamenti
Informazioni
to…
Articoli di Mario
Attività
-
Just finished the course “Synthetic Data as the Future of AI Privacy, Explainability, and Fairness: An Introduction for Data Scientists and Data…
Just finished the course “Synthetic Data as the Future of AI Privacy, Explainability, and Fairness: An Introduction for Data Scientists and Data…
Consigliato da Mario Scriminaci
-
⚖ Fairness in training of ML Models is an important topic that is not often addressed adequately enough. We've all heard the stories of biased…
⚖ Fairness in training of ML Models is an important topic that is not often addressed adequately enough. We've all heard the stories of biased…
Consigliato da Mario Scriminaci
-
I just had to perform some ad-hoc data analysis. What would have taken me before ~10min is now a matter of seconds. Can't get much faster than that…
I just had to perform some ad-hoc data analysis. What would have taken me before ~10min is now a matter of seconds. Can't get much faster than that…
Consigliato da Mario Scriminaci
Esperienza e formazione
Licenze e certificazioni
-
Pragmatic Management - Level III
Pragmatic Institute (Pragmatic Marketing + TDI)
Emissione:ID credenziale PMC-III
Pubblicazioni
-
ContentWise Impressions: An Industrial Dataset with Impressions Included
Proceedings of the 29th ACM International Conference on Information & Knowledge Management
In this article, we introduce the dataset dataset, a collection of implicit interactions and impressions of movies and TV series from an Over-The-Top media service, which delivers its media contents over the Internet. The dataset is distinguished from other already available multimedia recommendation datasets by the availability of impressions, idest the recommendations shown to the user, its size, and by being open-source. We describe the data collection process, the preprocessing applied, its…
In this article, we introduce the dataset dataset, a collection of implicit interactions and impressions of movies and TV series from an Over-The-Top media service, which delivers its media contents over the Internet. The dataset is distinguished from other already available multimedia recommendation datasets by the availability of impressions, idest the recommendations shown to the user, its size, and by being open-source. We describe the data collection process, the preprocessing applied, its characteristics, and statistics when compared to other commonly used datasets. We also highlight several possible use cases and research questions that can benefit from the availability of user impressions in an open-source dataset. Furthermore, we release software tools to load and split the data, as well as examples of how to use both user interactions and impressions in several common recommendation algorithms.
Altri autoriVedi pubblicazione -
Outfit Completion and Clothes Recommendation
Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems
Recommending fashion outfits requires learning a concept of style and fashionability that is typically human. There has been an increasing research effort into creating Machine Learning models able to learn such concepts, in order to distinguish between compatible and incompatible clothes and to select an item that would complete an outfit. However, most of the work done in literature tackles this problem from a pure Machine Learning point of view, disregarding real-case scenarios and the human…
Recommending fashion outfits requires learning a concept of style and fashionability that is typically human. There has been an increasing research effort into creating Machine Learning models able to learn such concepts, in order to distinguish between compatible and incompatible clothes and to select an item that would complete an outfit. However, most of the work done in literature tackles this problem from a pure Machine Learning point of view, disregarding real-case scenarios and the human interaction with systems able to generate outfits. This work tries to move the problem of generating outfits to the Recommender Systems domain by presenting as its main contribution a novel algorithm for a fashion-specific Recommender System that generates fashionable outfits, able to scale its inference time to be useful in real use case scenarios, and applies such algorithm on public and industrial datasets. In addition to this, this work shows preliminary results on how this algorithm can be employed in a real scenario and reports as preliminary results the evaluations provided by three professional stylists on the outfits generated by such algorithms.
Altri autoriVedi pubblicazione -
A Modular Framework for Versatile Conversational Agent Building
IEEE Computer Society Washington, DC, USA ©2011
This paper illustrates a web-based infrastructure of an architecture for conversational agents equipped with a modular knowledge base. This solution has the advantage to allow the building of specific modules that deal with particular features of a conversation (ranging from its topic to the manner of reasoning of the chatbot). This enhances the agent interaction capabilities. The approach simplifies the chatbot knowledge base design process: extending, generalizing or even restricting the…
This paper illustrates a web-based infrastructure of an architecture for conversational agents equipped with a modular knowledge base. This solution has the advantage to allow the building of specific modules that deal with particular features of a conversation (ranging from its topic to the manner of reasoning of the chatbot). This enhances the agent interaction capabilities. The approach simplifies the chatbot knowledge base design process: extending, generalizing or even restricting the chatbot knowledge base in order to suit it to manage specific dialoguing tasks as much as possible.
Altri autoriVedi pubblicazione -
Multi-directional Detection of Scratches in Digitized Images
17th European Signal Processing Conference (EUSIPCO 2009)
Line scratches are common defects in old archived videos. Many printed images suffer of a similar problem, in most cases due to improper handling or inaccurate preservation of the support. Once an image is digitized, its defects be- come part of that image. Many state-of-the-art papers deal with long, thin, vertical lines in old movie frames, by ex- ploiting both spatial and temporal information. In this paper we present a method that consistently modifies and extends our previous proposed…
Line scratches are common defects in old archived videos. Many printed images suffer of a similar problem, in most cases due to improper handling or inaccurate preservation of the support. Once an image is digitized, its defects be- come part of that image. Many state-of-the-art papers deal with long, thin, vertical lines in old movie frames, by ex- ploiting both spatial and temporal information. In this paper we present a method that consistently modifies and extends our previous proposed algorithm, to detect line scratches in digitized still images. Our method is able to detect scratches regardless of their orientation, and to draw their contour by labeling the pixels belonging to them.
Altri autoriVedi pubblicazione -
Sub-Symbolic Mapping of Cyc Microtheories in Data-Driven Conceptual Spaces
Proc of 11th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2007)
The presented work aims to combine statistical and cognitive-oriented approaches with symbolic ones so that a conceptual similarity relationship layer can be added to a Cyc KB microtheory. Given a specific microtheory, a LSA-inspired conceptual space is inferred from a corpus of texts created using both ad hoc extracted pages from the Wikipedia repository and the built-in comments about the concepts of the specific Cyc microtheory. Each concept is projected in the conceptual space and the…
The presented work aims to combine statistical and cognitive-oriented approaches with symbolic ones so that a conceptual similarity relationship layer can be added to a Cyc KB microtheory. Given a specific microtheory, a LSA-inspired conceptual space is inferred from a corpus of texts created using both ad hoc extracted pages from the Wikipedia repository and the built-in comments about the concepts of the specific Cyc microtheory. Each concept is projected in the conceptual space and the desired layer of subsymbolic relationships between concepts is created. This procedure can help a user in finding the concepts that are "sub-symbolically conceptually related" to a new concept that he wants to insert in the microtheory. Experimental results involving two Cyc microtheories are also reported.
Altri autoriVedi pubblicazione
Progetti
-
ContentWise
- Presente
Full control over each personalized user interface element across platforms through a set of visual layout tools, without changes to client code. The most sophisticated content discovery solution, with algorithmic and social recommendations, predictive browsing and context awareness. Content programmers achieve unprecedented control thanks to predictive performance tools, curation, dynamic streams, business rules, A/B testing.
Altri creatoriVedi progetto -
OpenInFSE
-
The OpenInFSE project aims at realizing an Italian interoperability framework for Electronic Health Record (EHR) systems. This framework is expected to make operational the infrastructure architectural model for interoperability of EHRs, named InFSE, whose specifications have been defined under a Convention between the Department for the digitalization of public administration and technological innovation (DDI - Presidency of the Council of Ministers) and the ICT Department of the Italian…
The OpenInFSE project aims at realizing an Italian interoperability framework for Electronic Health Record (EHR) systems. This framework is expected to make operational the infrastructure architectural model for interoperability of EHRs, named InFSE, whose specifications have been defined under a Convention between the Department for the digitalization of public administration and technological innovation (DDI - Presidency of the Council of Ministers) and the ICT Department of the Italian National Research Council (CNR).
Altri creatoriVedi progetto -
Mio Television
-
MiO is an innovative media delivery platform that revolutionizes the market providing full personalization of user experience.
Through MiO media platform the users are able to access their favorite programs, individualized through advanced correlation techniques.Altri creatoriVedi progetto
Lingue
-
Italian
Conoscenza madrelingua o bilingue
-
English
Conoscenza professionale completa
Referenze ricevute
6 persone hanno scritto una referenza per Mario
Iscriviti ora per vedereAltre attività di Mario
-
Gartner predicts 75% (!) of all businesses will use GenAI to create synthetic customer data by 2026. That's 18 months from now! Is your business…
Gartner predicts 75% (!) of all businesses will use GenAI to create synthetic customer data by 2026. That's 18 months from now! Is your business…
Consigliato da Mario Scriminaci
-
Love to see Synthetic Data leader MOSTLY AI (where I started in the privacy tech space) on this list and of course, super proud of the work we're…
Love to see Synthetic Data leader MOSTLY AI (where I started in the privacy tech space) on this list and of course, super proud of the work we're…
Consigliato da Mario Scriminaci
-
🚨 3.6 billion location datapoints revealing the exact movements of military personnel and millions of citizens. This isn't a leak—it's a free data…
🚨 3.6 billion location datapoints revealing the exact movements of military personnel and millions of citizens. This isn't a leak—it's a free data…
Consigliato da Mario Scriminaci
-
Ieri a Roma presso la Sala Zuccari del Senato della Repubblica si è tenuto l'evento “Intelligenza artificiale e dati: quale futuro?”, promosso da…
Ieri a Roma presso la Sala Zuccari del Senato della Repubblica si è tenuto l'evento “Intelligenza artificiale e dati: quale futuro?”, promosso da…
Consigliato da Mario Scriminaci
-
🔍 Unlocking Fairness in AI with Synthetic Data! 🌐 Excited to share my latest blog post on the MOSTLY AI Platform’s innovative approach to tackling…
🔍 Unlocking Fairness in AI with Synthetic Data! 🌐 Excited to share my latest blog post on the MOSTLY AI Platform’s innovative approach to tackling…
Condiviso da Mario Scriminaci
Altri profili simili
Altre persone che si chiamano Mario Scriminaci
Su LinkedIn ci sono altre 2 persone che si chiamano Mario Scriminaci
Vedi altre persone che si chiamano Mario Scriminaci