Image based scene understanding in autonomous driving applications is typically performed directly in image space, making both the detection of general objects and their accurate 3-d localization challenging. Recent developments in the field of deep learning based stereo reconstruction offer an alternate path to tackling these challenges. I will present a surround multi camera stereo system, recently developed at Mobileye, which was designed to offer a new sensing mode of the vehicle's surrounding. This mode is algorithmically independent from our classic vision pipeline and sensor-independent from our LiDAR based detection. I will mention some design considerations regarding our datasets, losses, and architecture, particularly with regards to performing depth reconstruction using multiple overlapping fields-of-view with an arbitrary camera setup.

Dr. Ofer Springer received his PhD from the Hebrew University of Jerusalem where he applied machine learning and explicit statistical models to observational challenges in astrophysics, such as mapping dark matter in galaxy clusters and detecting lensed quasars. Ofer is now a Mobileye Fellow of Computer Vision algorithms and leads a research team developing vision based 3D perception for autonomous driving applications.

AI enables principled representation of knowledge, complex strategy optimization, learning from data, and support to human decision making. I will present examples and discuss the scope of AI in our research in the finance domain.

Manuela M. Veloso is the Head of J.P. Morgan AI Research, which pursues fundamental research in areas of core relevance to financial services, including data mining and cryptography, machine learning, explainability, and human-AI interaction. J.P. Morgan AI Research partners with applied data analytics teams across the firm as well as with leading academic institutions globally. Professor Veloso is on leave from Carnegie Mellon University as the Herbert A. Simon University Professor in the School of Computer Science, and the past Head of the Machine Learning Department. With her students, she had led research in AI, with a focus on robotics and machine learning, having concretely researched and developed a variety of autonomous robots, including teams of soccer robots, and mobile service robots. Her robot soccer teams have been RoboCup world champions several times, and the CoBot mobile robots have autonomously navigated for more than 1,000km in university buildings. Professor Veloso is the Past President of AAAI, (the Association for the Advancement of Artificial Intelligence), and the co-founder, Trustee, and Past President of RoboCup. Professor Veloso has been recognized with a multiple honors, including being a Fellow of the ACM, IEEE, AAAS, and AAAI. She is the recipient of several best paper awards, the Einstein Chair of the Chinese Academy of Science, the ACM/SIGART Autonomous Agents Research Award, an NSF Career Award, and the Allen Newell Medal for Excellence in Research. Professor Veloso earned a Bachelor and Master of Science degrees in Electrical and Computer Engineering from Instituto Superior Tecnico in Lisbon, Portugal, a Master of Arts in Computer Science from Boston University, and Master of Science and PhD in Computer Science from Carnegie Mellon University. See www.cs.cmu.edu/~mmv/Veloso.html for her scientific publications.

We will illustrate the focus on customer, and the value of inventing on behalf of customers through 2 examples: the Just Walk Out technology behind Amazon Go, a store where you shop and never have to wait in line, and a peek under the hood of Amazon One, a fast, convenient, contactless way for people to use their palm to make everyday activities like paying at a store, presenting a loyalty card, entering a location like a stadium, or badging into work more effortless.

Professor Gérard Medioni received the Diplôme d’Ingenieur from ENST, Paris in 1977, a M.S. and Ph.D. from the University of Southern California in 1980 and 1983 respectively. He is Vice President/Distinguished Scientist at Amazon, where he is leading the research efforts for Amazon Go, and he recently announced Amazon One service. He is also Professor Emeritus of Computer Science at USC, where he served as Chairman of the Computer Science Department from 2001 to 2007. Professor Medioni has made significant contributions to the field of computer vision. He has published 4 books, over 80 journal papers and 200 conference articles, and is the recipient of more than 45 patents. He is the editor, with Sven Dickinson, of the Computer Vision series of books for Morgan-Claypool. Prof. Medioni is on the advisory board of the IEEE Transactions on PAMI Journal, associate editor of the Pattern Recognition and Image Analysis Journal. He is vice president of the Computer Vision Foundation (CVF). Prof. Medioni serves at general co-chair of many CVPR Conferences (1997, 2001, 2007, 2009, 2020), ICPR (1998, 2014), WACV (2009, 2011, 2013, 2015, 2017, 2019, 2021, 2022), ICCV (2017, 2019). Prof. Medioni has been a consultant to several companies and startups (DXO, Poseidon, Opti-copy, Geometrix, Symah Vision, KLA-Tencor, PrimeSense) prior to joining Amazon. He is the recipient of the IEEE PAMI Mark Everingham Prize for contributions to the Computer Vision Community. He is a Fellow of IAPR, a Fellow of the IEEE, and a Fellow of AAAI.

The growing adaptation of machine learning in many areas especially healthcare, have led the adoption into production systems. The availability of large datasets may contain private and sensitive information. This poses serious privacy and security concerns, there are challenges when machine learning algorithm needs to access private data. In order to address these issues, several privacy-preserving deep learning techniques, including Secure Multi-Party Computation (SMPC) and Homomorphic Encryption (HE) have been adopted. There are also several methods to modify the model, so that it can be used in privacy-preserving environment. However, there is trade-off between privacy and performance among various techniques. In addition private data can be misused or leaked through various cyber threats, like when attacker could speculate properties of the data used for training, or find the underlying model architecture and parameters. In this session we will review the privacy concerns brought by machine learning, and the mitigating techniques introduced to tackle these issues.

Dr. Mendel was the General Manager Cybersecurity COE at Intel. He is a serial cybersecurity entrepreneur; He has been the CEO and Co-Founder of SCsquare Ltd., where he founded a business enabler for advanced cybersecurity technologies. Dr. Mendel holds 16 approved patents in the area of cybersecurity. His career in cybersecurity over the past 20 years is a unique mixture of broad practical experience and research expertise. His practice included extensive involvement in cybersecurity offensive projects, research and development, business development and product management. Proven worldwide track records in secure operating systems, digital rights management (DRM), security certification (CC, FIPS, EMV), penetration test, reverses engineering, Machine Learning, Blockchain, IoT security and Smart Grid cybersecurity. His academic research topics includes: economic perspective of cybersecurity attacks, Quantum, Blockchain technology with a special focus on cybersecurity attacks, privacy issues and business continuation under cyber-attack.

The talk will discuss recent trends in computer vision, with a personal view of their successes, limitations and future directions.

Shimon Ullman is the Samy and Ruth Cohn Professor of Computer Science at the Weizmann Institute of Science, and the head of the Weizmann Institute AI Center. Prior to this position, he was a Professor at the Brain and Cognitive Science and the AI Laboratory at MIT. His areas of research combine computer and human vision, human cognition, and brain modeling. He obtained his B.Sc. in Mathematics, Physics and Biology, at the Hebrew University of Jerusalem, and Ph.D. in Electrical Engineering and Computer Sciences, at the Artificial Intelligence Laboratory in the Massachusetts Institute of Technology. He is a recipient of the 2008 David. E. Rumelhart Prize in human cognition, the 2014 Emet Prize for Art, Science and Culture, the 2015 Israel Prize in Computer Science, and the 2019 IEEE Azriel Rosenfeld Award for lifetime achievement in computer vision. He is a member of the Israeli Academy of Sciences and Humanities, and the American Academy of Arts and Sciences.

Learning to separate data into its meaningful attributes is a core task in machine learning. The performance of current methods leaves much to be desired, mainly due to their reliance on generative adversarial networks (GANs). In this work, we consider the setting in which some attributes are observed, and our task is to infer the unobserved attributes. We present a new non-adversarial approach - LORD -  that is highly effective for this task.  Strikingly, we discover that latent optimization provides an extremely potent inductive bias, and additionally we show that GANs are not necessary for disentanglement but rather they contribute towards generating sharp images. Finally, we demonstrate that our method outperforms the top unsupervised image translation methods.

Yedid Hoshen is an Assistant Professor at the School of Computer Science and Engineering, the Hebrew University of Jerusalem. His current research interests include Deep Generative Models, Representation Disentanglement and Anomaly Detection. Recently, he was a Research Scientist at Facebook AI Research. He completed his PhD at the Hebrew University of Jerusalem, supervised by Prof. Shmuel Peleg. Previously he studied Physics at the University of Oxford, traded options (volatility arbitrage) for a prop desk at KBC-FP, designed mission control algorithms for the Israeli Space Program and worked at Google ([x] and Research).

Very recently, square loss has been observed to perform well in classification tasks with deep networks. However, a theoretical justification is lacking, unlike the cross-entropy case for which an asymptotic analysis is available. I will sketch several observations on the dynamics of gradient flow under the square loss in ReLU networks. In particular, I will show how convergence to a local minimum norm solution is expected when normalization techniques such as Batch Normalization (BN) or Weight Normalization (WN) are used. The main property of the minimizer that bounds its expected error is its norm: among all the interpolating solutions, the ones associated with smaller Frobenius norms of the weight matrices have better margin and better bounds on the expected classification error.

Tomaso A. Poggio, is a physicist whose research has always been between brains and computers. It is now focused on the mathematics of deep learning and on the computational neuroscience of the visual cortext. He is the Eugene McDermott Professor in the Dept. of Brain & Cognitive Sciences at MIT and the director of the NSF Center for Brains, Minds and Machines at MIT. Among other awards he received the 2014 Swartz Prize for Theoretical and Computational Neuroscience and the IEEE 2017 Azriel Rosenfeld Lifetime Achievement Award. A former Corporate Fellow of Thinking Machines Corporation, a former director of PHZ Capital Partners, Inc. and of Mobileye, he was involved in starting, or investing in, several other high tech companies including Arris Pharmaceutical, nFX, Imagen, Digital Persona, Deep Mind and Orcam.

Many deaths occur in hospitals and clinics due to preventable medical errors. In this talk, Dr. Fei-Fei Li will share her recent research into how electronic sensors and artificial intelligence can help medical professionals monitor and treat vulnerable patients in ways that improve outcomes while respecting privacy.

Dr. Fei-Fei Li is the inaugural Sequoia Professor in the Computer Science Department at Stanford University, and Co-Director of Stanford’s Human-Centered AI Institute. She served as the Director of Stanford’s AI Lab from 2013 to 2018. And during her sabbatical from Stanford from January 2017 to September 2018, she was Vice President at Google and served as Chief Scientist of AI/ML at Google Cloud. Dr. Fei-Fei Li obtained her B.A. degree in physics from Princeton in 1999 with High Honors, and her PhD degree in electrical engineering from California Institute of Technology (Caltech) in 2005. She joined Stanford in 2009 as an assistant professor. Prior to that, she was on faculty at Princeton University (2007-2009) and University of Illinois Urbana-Champaign (2005-2006). Dr. Fei-Fei Li’s current research interests include cognitively inspired AI, machine learning, deep learning, computer vision and AI+healthcare especially ambient intelligent systems for healthcare delivery. In the past she has also worked on cognitive and computational neuroscience. Dr. Li has published more than 200 scientific articles in top-tier journals and conferences, including Nature, PNAS, Journal of Neuroscience, CVPR, ICCV, NIPS, ECCV, ICRA, IROS, RSS, IJCV, IEEE-PAMI, New England Journal of Medicine, Nature Digital Medicine, etc. Dr. Li is the inventor of ImageNet and the ImageNet Challenge, a critical large-scale dataset and benchmarking effort that has contributed to the latest developments in deep learning and AI. In addition to her technical contributions, she is a national leading voice for advocating diversity in STEM and AI. She is co-founder and chairperson of the national non-profit AI4ALL aimed at increasing inclusion and diversity in AI education. Dr. Li is an elected Member of the National Academy of Engineering (NAE) and the National Academy of Medicine (NAM). She is also a Fellow of ACM, a member of the Council on Foreign Relations (CFR), a recipient of the 2019 IEEE PAMI Longuet-Higgins Prize, 2019 National Geographic Society Further Award, 2017 Athena Award for Academic Leadership, IAPR 2016 J.K. Aggarwal Prize, the 2016 IEEE PAMI Mark Everingham Award, the 2016 nVidia Pioneer in AI Award, 2014 IBM Faculty Fellow Award, 2011 Alfred Sloan Faculty Award, 2012 Yahoo Labs FREP award, 2009 NSF CAREER award, the 2006 Microsoft Research New Faculty Fellowship, among others. Dr. Li is a keynote speaker at many academic or influential conferences, including the World Economics Forum (Davos), the Grace Hopper Conference 2017 and the TED2015 main conference. Work from Dr. Li's lab have been featured in a variety of magazines and newspapers including New York Times, Wall Street Journal, Fortune Magazine, Science, Wired Magazine, MIT Technology Review, Financial Times, and more. She was selected as a 2017 Women in Tech by the ELLE Magazine, a 2017 Awesome Women Award by Good Housekeeping, a Global Thinker of 2015 by Foreign Policy, and one of the “Great Immigrants: The Pride of America” in 2016 by the Carnegie Foundation, past winners include Albert Einstein, Yoyo Ma, Sergey Brin, et al.