Home      Log In      Contacts      FAQs      INSTICC Portal
 

Keynote Lectures

More than Meets the Eye: Towards an Artificial Intelligence Observatory
Matias Carrasco Kind, University Illinois Urbana Champaign, United States

Towards Recognizing New Semantic Concepts in new Visual Domains
Barbara Caputo, Politecnico di Torino, Italy

Deep Learning for Biometric Systems: Applications and Trends
Fabio Scotti, Universita degli Studi di Milano, Italy

 

More than Meets the Eye: Towards an Artificial Intelligence Observatory

Matias Carrasco Kind
University Illinois Urbana Champaign
United States
 

Brief Bio
Matias Carrasco Kind is currently a Senior Research Scientist at the National Center for Supercomputing Applications (NCSA), Assistant Research Professor in Astronomy and the Associate Director of the Data Science Research Services at the Gies College of Business at the University of Illinois at Urbana-Champaign in the U.S.

He is interested in challenging problems involving data intensive science, machine, and deep learning, data mining, data analysis and visualization, image processing, AI generative models, scientific platforms and cyberinfrastructure, data management, software engineering, and scientific cloud computing, among others. Most of his research has been focused on Astrophysics but given the multidisciplinary nature of his work, and the common needs and tools across multiple fields regarding data, he has also applied these techniques to earth sciences, bio-imaging, veterinary, agricultural economics, finance research, and accounting.

Matias obtained his PhD in Astronomy with a Computational Science and Engineering option at the University of Illinois which focused on machine learning techniques applied to astronomy at large scales. 


Abstract
What if, by leveraging the rapid development of AI, cyber-infrastructure, and astronomical surveys we can create an extremely intelligent machine with infinite knowledge that after being feed with all of the available survey data from all the sources and wavelengths is able to recreate every observation for any object in any wavelength? What if we can feed that entity with an optical image and ask for a radio counterpart? Or ask it to generate infrared data from a given set of properties? Will, that machine been able to make inferences from new observations, assuming its infinite memory?

Even though this might sound too much science-fiction, 10 to 15 years from now might be an incubating project which needs to start today. In this talk, I'll discuss what efforts have been made in this direction, what deep learning advances might help us think in that future, how data from multiple surveys and telescopes can be combined in taking the first steps, and what have we done to make this happen.

Thanks to the advancement of computing, AI, and gateways techniques, the possibilities are countless, and it is now that we need to think about these issues in order to be prepared and to understand how information can be extracted intelligently in favor of scientific discoveries.



 

 

Towards Recognizing New Semantic Concepts in new Visual Domains

Barbara Caputo
Politecnico di Torino
Italy
 

Brief Bio
Barbara Caputo is Full Professor at Politecnico of Torino, where she leads the ELLIS Unit on Safe and Secure Sensing Machines. Since 2017 she has a double affiliation with the Italian Institute of Technology (IIT). She received her PhD in computer science from KTH, Stockholm (SE) in 2005. From 2007 till 2013 she was Senior Researcher at Idiap-EPFL (CH); she then moved to Sapienza Rome University, and joined Politecnico di Torino in 2018. She is an ERC Laureate, ELLIS Fellow and since 2019 she serves on the ELLIS board. She is one of the 30 experts who wrote the Italian Strategy on AI, and she is the coordinator of the Italian National PhD on AI & Industry 4.0, sponsored by the Ministry of Science.


Abstract
Deep learning is the leading paradigm in computer vision. However, deep models heavily rely on large scale annotated datasets for training. Unfortunately, labeling data is a costly and time-consuming process and datasets cannot capture the infinite variability of the real world. Therefore, deep neural networks are inherently limited by the restricted visual and semantic information contained in their training set. In this talk, I argue that it is crucial to design deep neural architectures that can operate in previously unseen visual domains and recognize novel semantic concepts. I will present different solutions to enable deep models to generalize to new visual domains, by transferring knowledge from a labeled source domain(s) to a domain (target) where no labeled data are available. I will then show how to extend the knowledge of a pre-trained deep model incorporating new semantic concepts, without having access to the original training set. Finally, I will introduce a more challenging problem: given images of multiple domains and semantic categories (with their attributes), how to build a model that recognizes images of unseen concepts in unseen domains? This can be tackled with an approach based on domain and semantic mixing of inputs and features, which is a first, promising step towards solving this problem.



 

 

Deep Learning for Biometric Systems: Applications and Trends

Fabio Scotti
Universita degli Studi di Milano
Italy
 

Brief Bio

Fabio Scotti (Senior Member, IEEE) received the Ph.D. degree in computer engineering from the Politecnico di Milano, Milan, Italy, in 2003. He was an Assistant Professor at the Department of Information Technologies, Università degli Studi di Milano, Italy (2002-2015). He was an Associate Professor at the Department of Computer Science, Università degli Studi di Milano, Italy (2015-2020). He is a Full Professor at the Università degli Studi di Milano, Italy since 2020. 

Original results have been published in over 130 papers in international journals, proceedings of international conferences, books, book chapters, and patents. His current research interests include biometric systems, machine learning and computational intelligence, signal and image processing, theory and applications of neural networks, three-dimensional reconstruction, industrial applications, intelligent measurement systems, and high-level system design.

He is an Associate Editor of the IEEE Transactions on Human-Machine Systems and the IEEE Open Journal of Signal Processing. He is serving as Book Editor (Area Editor, section Less-constrained Biometrics) of the Encyclopedia of Cryptography, Security, and Privacy (3rd Edition), Springer. He has been an Associate Editor of the IEEE Transactions on Information Forensics and Security, Soft Computing (Springer) and a Guest Coeditor for the IEEE Transactions on Instrumentation and Measurement.


Abstract
Applications, services and devices using biometric systems are continuously growing, and always new challenges must be faced by researchers. Adaptability, robustness to non-ideal conditions, real-time capability, high accuracy as well as improved interactions with the user, are strong requirements now present in innovative applications and solutions such as cyber security, smart devices and ambient intelligent infrastructures. Biometric systems are designed not just for identity recognition, but they can also be extremely useful to profile users and to understand the human behavior inferring their needs and desires. The presentation will focus on innovative biometric recognition approaches and systems, with specific focus on recent approaches based on artificial intelligence showing how recent deep learning techniques are capable to learn discriminative features directly from complex multidimensional signals and images as well as increasing the accuracy, adaptability, and robustness to non-ideal conditions of biometric systems with respect to traditional approaches. The talk presents biometric systems from a technological point of view and provides an outlook of recent artificial intelligence approaches, including deep learning methods with current strong points and limitations. A review of new applications of biometric systems and recent trends will be also presented. 



footer