The Best of Many Worlds: Scheduling Machine Learning Inference on CPU-GPU Integrated Architectures

Detailed info The Best of Many Worlds: Scheduling Machine Learning Inference on CPU-GPU Integrated Architectures AuthorsRafail Tsirbas, Giorgos Vasiliadis, Sotiris IoannidisTitleThe Best of Many Worlds: Scheduling Machine Learning Inference on…

Continue ReadingThe Best of Many Worlds: Scheduling Machine Learning Inference on CPU-GPU Integrated Architectures

Scalable neural architectures for end-to-end environmental sound classification

Detailed info Scalable neural architectures for end-to-end environmental sound classification AuthorsFrancesco Paissan, Alberto Ancilotto, Alessio Brutti, Elisabetta FarellaTitleScalable neural architectures for end-to-end environmental sound classificationAbstractSound Event Detection is a complex…

Continue ReadingScalable neural architectures for end-to-end environmental sound classification

MARVEL Data Corpus

One of the key outcomes of the MARVEL project is the so-called Data Corpus, which aims to give the possibility SMEs, start-ups, as well as the scientific and research communities to build on top of open datasets that will become available from MARVEL pilots and create new business by exploring extreme-scale multimodal analytics, evolving existing algorithms and more.

Continue ReadingMARVEL Data Corpus

MARVEL at the Ital-IA 2022

Our partner, Fondazione Bruno Kessler (FBK), represented by Luca Zanella outlined FBK’s contribution to MARVEL’s progress through his presentation titled “Responsible AI at the edge: towards privacy-preserving smart cities” at the Workshop titled “AI Responsabile e Affidabile” that was held on February 10th, 2022, as part of the Ital-IA 2022, with more than 30 attendees.

Continue ReadingMARVEL at the Ital-IA 2022