Report from NeurIPS 2022, New Orleans, LA (USA)

Report from NeurIPS 2022, New Orleans, LA (USA)

Presentation at NeurIPS 2022, "Symmetries and Geometry in Neural Representations" Workshop (NeurReps) Workshop website | NeurIPS website Last week, some of our members went to New Orleans for the thirty-sixth Conference on Neural Information Processing Systems, one of the biggest gatherings of machine learning researchers from all over the world. Having the chance to bring part of our association to NeurIPS 2022 was a great honour for us. We took part in multiple events. Simone Azeglio and Arianna Di Bernardo co-organised with Sophia Sanborn, Nina Miolane and Christian Shewmake the wonderful Symmetry and Geometry in Neural Representations (NeurReps) workshop gathering together researchers at the intersection of geometric deep learning, applied geometry, and neuroscience (Taco Cohen, Irina Higgins and many more) to study the geometric principles underlying neural representations. Secondly, our members Luca Bottero, Francesco Calisto and Valerio Pagliarino presented their work on learning geometrical features from images through group action enforcement in the poster session (https://openreview.net/forum?id=sEn61s0M1hy).They proposed an autoencoder architecture capable of...
Read More
MLJC project in Geometric DL accepted at NeurIPS 2022, New Orleans (USA)

MLJC project in Geometric DL accepted at NeurIPS 2022, New Orleans (USA)

We are delighted to announce that a group from MLJC including Luca Bottero, Francesco Calisto and Valerio Pagliarino will present their work at the world-leading conference NeurIPS 2022 (Neural Information Processing Systems) in the Neur-Reps (https://www.neurreps.org/) (Symmetries and Geometry in Neural Representations) workshop. The conference will take place in New Orleans, Louisiana (USA) from November, 27th to December 3rd. The project is inserted in the landscape of Geometric Deep Learning (GDL), a relatively recent branch of Machine Learning aiming at studying how to enforce geometrical structures and priors into ML models, whit the final goal of increasing performances, generalization capabilities and explainability. This specific work, titled Unsupervised Learning of Geometrical Features from Images by explicit Group Action Enforcement, has the ability of automatically disentangling the geometric rototranslational and scaling features from the intrinsic ones, when creating a latent representation of a dataset of input images. This line of research may lead in future to the development of more powerful and efficient architectures...
Read More

MLJC meets the Minister of the State of North Rhine-Westphalia, dr Stephan Holthoff-Pförtner

Questa mattina, 15 febbraio 2022, il Machine Learning Journal Club ha incontrato a Torino il ministro per gli Affari Federali, Europei e Internazionali della Renania settentrionale - Vestfalia Stephan dr Holthoff-Pförtner. All'incontro era presente anche il console generale a Milano dr Ingrid Jung. Il Ministro era a Torino per la firma di una Dichiarazione di Intenti per la collaborazione e lo sviluppo di relazioni amichevoli tra la Regione Piemonte e il Land tedesco della Renania settentrionale-Vestfalia sui temi dell'idrogeno, dell'intelligenza artificiale, della guida autonoma e dell'agricoltura di qualità. [1] L'incontro ha avuto come principale tema di discussione il rapporto tra intelligenza artificiale ed etica: è emerso come la collaborazione interdisciplinare tra tecnologi e umanisti sia oggi indispensabile per guidare lo sviluppo dell'AI esplorandone al massimo le potenzialità e mantenendo al centro l'uomo. All'incontro erano presenti Don Luca Peyron, giurista, teologo, docente presso l'Università di Torino del corso di "Spiritualità delle tecnologie emergenti", Faculty Fellow del Centro Nexa del Politecnico di Torino ed esperto...
Read More
MLJC visiting HPC4AI

MLJC visiting HPC4AI

Last week a team from MLJC visited the HPC4AI data center hosted by the Computer Science Department of the University of Turin (coord. Prof. Marco Aldinucci). We are grateful to HPC4AI for this opportunity and for providing our association with the computing power that is crucial for developing projects in the field of ML. For this reason HP4AI is not only at the forefront for computing solutions, service reliability and environmental compatibility, but as well for the opportunities targeting motivated students. Special thanks to proff. M. Aldinucci, C. Mattutino, M. Beccuti and Ing. S. Rabellino. Durante la scorsa settimana una delegazione di MLJC ha visitato il data center HPC4AI, situato presso il Dipartimento di Informatica - Università degli Studi di Torino - coord. Prof. Marco Aldinucci. Ci teniamo ad esprimere tutta la nostra gratitudine ad HPC4AI per averci dato questa opportunità e per la potenza di calcolo che mette a disposizione per le nostre attività tecniche in ambito Machine Learning. Per...
Read More
Meet MLJC in Turin at SHARPER – European Researchers’ Night

Meet MLJC in Turin at SHARPER – European Researchers’ Night

Report from the MLJC stand at SHARPER Castello del Valentino - Photo credits: https://commons.wikimedia.org/wiki/File:Castello_del_Valentino_(8062075958).jpg The Machine Learning Journal Club will be present at the SHARPER - European Researchers' Night in Turin on September 24th 2021, organized by the University of Turin and Politecnico of Turin. The title of the stand will be "MACHINE LEARNING E L’INTELLIGENZA ARTIFICIALE DEL FUTURO". At our stand, we will showcase our projects and activities through posters, presentations, videos and some electronic prototypes spacing from Scientific Machine Learning to Brain-Computer Interfaces. You will be able to meet our team and have a good chat about Machine Learning, Artificial Intelligence and emerging technologies in these fields in the beautiful frame of the Castello del Valentino in Turin. See you there! Visit the website of SHARPER: https://www.sharper-night.it/sharper-torino/ Discover the program: Click here for PDF ...
Read More
MLJC starts new project on Realtime Scientific Machine Learning

MLJC starts new project on Realtime Scientific Machine Learning

We are now ready for the next stage: our new projects on #BCIs and Realtime Scientific Machine Learning (by exploiting Xilinx's #FPGAs + NVIDIA Jetson Xavier) can finally take place. Further updates are coming on our website (www.mljc.it) as well as a more detailed prospectus. The MLJC would like to express special appreciation to NPO Torino s.r.l. for providing us with this equipment and to Università degli Studi di Torino and HPC4AI for their support to our activities. Luca Peyron Massimo Altamore Francesco Dipietromaria#machinelearning#ai#innovation#deeplearning#mljc https://www.linkedin.com/feed/update/urn:li:activity:6824315128419237888 ...
Read More

Machine Learning Journal Club selected in the EO Dashboard Hackathon by ESA, NASA, JAXA

We are glad to announce that the Machine Learning Journal Club team, composed by Beatrice Villata Andrea Semeraro Luca Pezzini Micol Olocco and Luca Bottero , has been selected as one of the finalist competitors in the EO Dashboard Hackathon (https://lnkd.in/dWRtmkq), organized by NASA - National Aeronautics and Space Administration, European Space Agency - ESA and JAXA: Japan Aerospace Exploration Agency!Together with 31 other projects, our project about "How was the lockdown from up there? A cross-country comparison in air quality" has been chosen among the 232 submitted in total. Proud of the possibility to compete against amazing teams, we wish everyone good luck!#ai #research #m #machinelearning #mljc #nasa #space #science https://www.linkedin.com/feed/update/urn:li:activity:6825368389255475200 ...
Read More