Banner
Home      Log In      Contacts      FAQs      INSTICC Portal
 
Documents

Keynote Lectures

Deep Learning for Wearable Biometrics
Emanuele Maiorana, Roma Tre University, Italy

Past, Present, Future, and Far Future of AI
Jürgen Schmidhuber, KAUST AI Initiative, Kingdom of Saudi Arabia; Swiss AI Lab IDSIA, Switzerland and NNAISENSE, Switzerland

New Synergies Between Deep Learning and Kernel Machines
Johan Suykens, KU Leuven, Belgium

 

Deep Learning for Wearable Biometrics

Emanuele Maiorana
Roma Tre University
Italy
 

Brief Bio
Emanuele Maiorana received the Ph.D. degree in biomedical, electromagnetism, and telecommunication engineering with European Doctorate Label from Roma Tre University, Rome, Italy, in 2009. He is currently a tenure track Assistant Professor with the Section of Applied Electronics, Department of Industrial, Electronic and Mechanical Engineering, Roma Tre University, Rome, Italy. His research interests are in the area of digital signal and image processing, with specific emphasis on biometric recognition. He is an Associate Editor of the IEEE Transactions on Information Forensics and Security since 2020. He is the recipient of the Lockheed Martin Best Paper Award for the Poster Track at the IEEE Biometric Symposium 2007, the Honeywell Student Best Paper Award at the IEEE Biometrics: Theory, Applications and Systems conference 2008, and the Best Paper Award at the International Conference on Pattern Recognition Applications and Methods (ICPRAM). He was the General Chair of the IEEE International Workshop on Biometrics and Forensics (IWBF) 2021, and he is the General Chair of the IEEE International Workshop on Information Forensics and Security (WIFS) 2024.


Abstract
Wearable devices are rapidly becoming widespread, to an extent that they have been often mentioned as the next big thing in personal computing after mobile devices. This is due to the several capabilities these devices can offer, exploited for applications ranging from monitoring fitness or health-related parameters to controlling virtual reality avatars.
In addition to their existing functionalities, wearable devices intrinsically offer the possibilities of being exploited for biometric recognition purposes. In fact, the physiological characteristics they can capture typically possess unique properties that could enable the identification of legitimate subjects and the detection of unauthorized usage.
This lecture will delve into the latest advancements in this domain, examining the current state of the art along with associated unresolved issues. More specifically, the techniques relying on deep learning approaches that can be employed to implement reliable and efficient biometric recognition systems based on wearable devices will be illustrated. Systems leveraging traits such as photoplethysmogram (PPG), electrodermal activity (EDA), and seismocardiogram (SCG) will be explored as illustrative examples.



 

 

Past, Present, Future, and Far Future of AI

Jürgen Schmidhuber
KAUST AI Initiative, Kingdom of Saudi Arabia; Swiss AI Lab IDSIA, Switzerland and NNAISENSE
Switzerland
 

Brief Bio
The New York Times headlined: "When A.I. Matures, It May Call Jürgen Schmidhuber 'Dad'." Since age 15, his main goal has been to build a self-improving A.I. smarter than himself, then retire. His lab's deep learning artificial neural networks have revolutionised machine learning and A.I. By 2017, they were on over 3 billion smartphones, and used billions of times per day, for Facebook’s automatic translation, Google’s speech recognition, Google Translate, Apple’s Siri & QuickType, Amazon’s Alexa, etc. He pioneered the principles of artificial curiosity & generative adversarial networks (1990, now widely used), neural network distillation (1991, now widely used), self-supervised pre-training for deep learning (1991, the "P" in "ChatGPT" stands for "pre-trained"), unnormalised linear Transformers (1991, the "T" in "ChatGPT" stands for "Transformer"), and meta-learning machines that learn to learn (since 1987). His lab also produced LSTM, the most cited AI of the 20th century, and the LSTM-inspired Highway Net, the first very deep feedforward net with hundreds of layers (ResNet, the most cited AI of the 21st century, is an open-gated Highway Net). Elon Musk tweeted: "Schmidhuber invented everything." He is recipient of numerous awards, Director of the AI Initiative at KAUST in KSA, Scientific Director of the Swiss AI Lab IDSIA, Adj. Prof. of A.I. at Univ. Lugano, and Co-Founder & Chief Scientist of the company NNAISENSE. He is a frequent keynote speaker at major events, and advising various governments on A.I. strategies.


Abstract
I’ll discuss modern Machine Learning, its historic context, and its expected impact on the future of the universe.



 

 

New Synergies Between Deep Learning and Kernel Machines

Johan Suykens
KU Leuven
Belgium
 

Brief Bio
Johan Suykens is a full Professor with KU Leuven. He is author of the books "Artificial Neural Networks for Modelling and Control of Non-linear Systems" (Springer) and "Least Squares Support Vector Machines" (World Scientific), co-author of the book "Cellular Neural Networks, Multi-Scroll Chaos and Synchronization" (World Scientific) and editor of the books "Nonlinear Modeling: Advanced Black-Box Techniques", "Advances in Learning Theory: Methods, Models and Applications" and "Regularization, Optimization, Kernels, and Support Vector Machines". He has served as associate editor for the IEEE Transactions on Neural Networks and Learning Systems and the IEEE Transactions on Artificial Intelligence and action editor of Neural Networks. He is a recipient of the International Neural Networks Society INNS 2000 Young Investigator Award for significant contributions in the field of neural networks. He has been recently awarded the 2024 IEEE CIS Neural Networks Pioneer Award. He has served as a Director and Organizer of the NATO Advanced Study Institute on Learning Theory and Practice 2002, as a program co-chair for the International Joint Conference on Neural Networks 2004 and the International Symposium on Nonlinear Theory and its Applications 2005, as an organizer of the International Symposium on Synchronization in Complex Networks 2007, as co-organizer of the NIPS 2010 workshop on Tensors, Kernels and Machine Learning, as chair of ROKS 2013 International Workshop on Advances in Regularization, Optimization, Kernel methods and Support vector machines, and as chair of DEEPK 2024 International Workshop on Deep Learning and Kernel Machines. He has been awarded an ERC Advanced Grant 2011 and 2017, has been elevated IEEE Fellow 2015 for developing least squares support vector machines, and is an ELLIS Fellow. He is currently serving as program director for the Master AI program at KU Leuven.


Abstract
In this talk we will focus on new connections between deep learning and kernel machines that are related to least squares support vector machines. We will explain how restricted kernel machine representations can be obtained from least squares support vector machines formulations, having several properties in common with restricted Boltzmann machines. It enables to realize new deep kernel machines, generative models, multi-view, disentangled, recurrent and tensor based models. Furthermore, we will discuss how attention mechanisms of transformers can be formulated as a variant of kernel singular value decomposition within the framework of least squares support vector machines. Primal and dual model representations can be characterized for attention mechanisms, in terms of query and key feature maps and asymmetric kernels, respectively. The new insights of the proposed Primal-Attention method provide low rank representations together with efficient training in the primal.



footer