Conférences - Réseaux de neurones et intelligence artificielle, apprentissage automatique - États-Unis

Machine Learning (ML) is quickly providing new powerful tools for physicists and other natural scientists to extract essential information from large amounts of data, either from experiments or simulations. This IPAM long program will foster nontrivial research and provoke scientific discussion at the interface between ML and Physics. We aim to go beyond simple fitting of physical models from data and move the discussion to (i) using generative ML methods and active learning in order to generate and design complex and novel physical structures and objects, (ii) obtain models that are physically understable, e.g. by maintaining relations of the predictions to the microscopic physical quantities used as an input, (iii) using ML to learn the physical principles and mathematical structures underlying the data, and (iv) developing new ML methods inspired by methods and models developed in Physics.

The ADT 2019 conference focus is on algorithmic decision theory broadly defined, seeking to bring together researchers and practitioners coming from diverse areas of Computer Science, Economics and Operations Research in order to improve the theory and practice of modern decision support.

Algorithms, Argumentation Theory, Artificial Intelligence, Computational Social Choice, Database Systems, Decision Analysis, Discrete Mathematics, Game Theory, Machine Learning, Matching, Multi-agent Systems, Multiple Criteria Decision Aiding, Networks, Optimization, Risk Management, and Utility Theory

Recherche opérationnelle,    Gestion des connaissances, Big Data Computing

Institute for Pure and Applied Mathematics (IPAM), UCLA

Part of the Long Program Machine Learning for Physics and the Physics of Learning.

In this workshop we will explore how to use physical intuition and ideas to design new classes of machine learning (ML) algorithms. Physics-inspired sampling algorithms could be used to train ML structures or sample the hyper-parameter space (e.g. deep Neural Networks). Additionally, physics-based models such as Ising/Potts models or energy-based models have influenced ML inference frameworks such as Markov Random Fields and Restricted Boltzmann Machines, and we want to continue the discussion to facilitate this innovation transfer. Finally, physical insight could be used to enhance learning in the situation of scarce data by enforcing smoothness, differentiability or other physical properties relevant to a given problem.

Géographie, géolocalisation, systèmes d'observation de la Terre,    Reconnaissance de formes et traitement d'image, vision par ordinateur

The conference provides a leading international forum for the dissemination of original research in ML, with emphasis on applications as well as novel algorithms and systems. Following the success of previous ICMLA conferences, the conference aims to attract researchers and application developers from a wide range of ML related areas, and the recent emergence of Big Data processing brings an urgent need for machine learning to address these new challenges. The conference will cover both machine learning theoretical research and its applications. Contributions describing machine learning techniques applied to real-world problems and interdisciplinary research involving machine learning, in fields like medicine, biology, industry, manufacturing, security, education, virtual environments, games, are especially encouraged.

American Meteorological Society (AMS)

Institute for Pure and Applied Mathematics (IPAM), UCLA

Rapid advances in deep learning techniques are starting to revolutionize medical imaging. Radiology, disease detection, and tissue imaging are all expected to be facilitated by automated image analysis programs in the near future. Many new interdisciplinary research questions arise; finding solutions with practical significance requires input from mathematicians, bio-physicists, and computational engineers. This workshop aims to bring together researchers from different backgrounds to explore this new frontier of science.

Mathématiques appliquées (en général),    Reconnaissance de formes et traitement d'image, vision par ordinateur

Applying ML & deep learning to create AI Assistants & conversational interfaces to create deeper, more personalised one-to-one customer experiences.

Institute for Pure and Applied Mathematics (IPAM), UCLA

Psychiatric disorders are typically diagnosed and evaluated using subjective psychological exams that assess symptoms, thoughts, feelings and behavioral patterns. Ongoing and recent advances in measurements provide EEG, functional MRI, optogenetic, genomic, and metabolic data. Along with mathematical methods developed to analyze these data, a more physiological and quantitative approach for diagnosis and treatment can be envisioned. This workshop will explore how modern computational tools and mathematical modeling can be integrated with measurements to improve psychiatric diagnosis and treatment.

Biométrie,    Soft computing, algorithmes évolutionnaires, domaine des métaheuristiques, logique floue

Organizations that successfully apply AI tools and strategies compete more effectively. Make plans to join us at the O'Reilly AI Conference and chart your business transformation.

IPAM

This workshop will bring together researchers working on the theoretical sides of deep learning techniques for perception and control of automated vehicles with researchers interested in assuring these autonomous systems operate with safety guarantees. Moreover, experts in sensing and imaging technology will be brought to the table, to cover the full pipeline from the collection of the data, over the AI theory and development, all the way to the software and actuation challenges. Additional themes addressed in this workshop include interactions between vehicle sensing and the infrastructure, and cybersecurity aspects related to sensing and machine learning (how to purposefully mislead sensors and AI).

Part of the Long Program Mathematical Challenges and Opportunities for Autonomous Vehicles

Mathématiques appliquées (en général),    Robotique, automation & mécatronique

Kavli Institute for Theoretical Physics (KITP)

The Large Hadron Collider (LHC) is the world’s facility for probing fundamental physics at the electroweak scale and well beyond. As it enters a new phase of extended data accumulation, two broad challenges emerge: how to fulfill the potential for percent-level precision with the large dataset, and how to maximise the information that can be extracted from each event about the underlying scattering process, in particular with machine learning. Solving these problems will have an impact across a wide range of physics topics: establishing the properties of the newly discovered interactions of the Higgs sector and understanding electroweak symmetry breaking, enhancing the sensitivity of searches for physics beyond the Standard Model (BSM), and precision measurements of a range of fundamental parameters in the Standard Model.