Search

Your search keyword '"Michal Valko"' showing total 7 results
Start Over Author "Michal Valko" Topic 02 engineering and technology
7 results on '"Michal Valko"'

1. Game Plan: What AI can do for Football, and What Football can do for AI

Author

Daniel Hennes, Gregory Thornton, Bart De Vylder, S. M. Ali Eslami, Trevor Back, Zhe Wang, Pauline Luc, Karl Tuyls, Alex Bridgland, Nathalie Beauguerlange, Rémi Munos, Praneet Dutta, Alexandre Galashov, Jerome T. Connor, Tim Waskett, William Spearman, Razia Ahamed, Mark Rowland, Andrew Jaegle, Dafydd Steele, Julien Perolat, Shayegan Omidshafiei, Simon Bouton, Jackson Broshear, Kris Cao, Paul Muller, Nicolas Heess, Michal Valko, Demis Hassabis, Marta Garnelo, Adrià Recasens, Ian Graham, Thore Graepel, Pablo Sprechmann, Romuald Elie, and Pol Moreno

Subjects
FOS: Computer and information sciences, Progress in artificial intelligence, Counterfactual thinking, Data collection, Computer Science - Artificial Intelligence, business.industry, Computer science, Multi-agent system, ComputingMilieux_PERSONALCOMPUTING, 02 engineering and technology, Football, Data science, Field (computer science), Artificial Intelligence (cs.AI), Computer Science - Computer Science and Game Theory, Artificial Intelligence, Analytics, 0202 electrical engineering, electronic engineering, information engineering, Computer Science - Multiagent Systems, 020201 artificial intelligence & image processing, business, Game theory, Computer Science and Game Theory (cs.GT), Multiagent Systems (cs.MA)
Abstract

The rapid progress in artificial intelligence (AI) and machine learning has opened unprecedented analytics possibilities in various team and individual sports, including baseball, basketball, and tennis. More recently, AI techniques have been applied to football, due to a huge increase in data collection by professional teams, increased computational power, and advances in machine learning, with the goal of better addressing new scientific challenges involved in the analysis of both individual players’ and coordinated teams’ behaviors. The research challenges associated with predictive and prescriptive football analytics require new developments and progress at the intersection of statistical learning, game theory, and computer vision. In this paper, we provide an overarching perspective highlighting how the combination of these fields, in particular, forms a unique microcosm for AI research, while offering mutual benefits for professional teams, spectators, and broadcasters in the years to come. We illustrate that this duality makes football analytics a game changer of tremendous value, in terms of not only changing the game of football itself, but also in terms of what this domain can mean for the field of AI. We review the state-of-the-art and exemplify the types of analysis enabled by combining the aforementioned fields, including illustrative examples of counterfactual analysis using predictive models, and the combination of game-theoretic analysis of penalty kicks with statistical learning of player attributes. We conclude by highlighting envisioned downstream impacts, including possibilities for extensions to other sports (real and virtual).

Published
2021
Full Text
View/download PDF

2. Compressing the Input for CNNs with the First-Order Scattering Transform

Author

Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko, Michal Valko, Valko, Michal, Inférence bayésienne à ressources limitées - données massives et modèles coûteux - - BoB2016 - ANR-16-CE23-0003 - AAPG2016 - VALID, Centre de vision numérique (CVN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec, Sequential Learning (SEQUEL), Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Organ Modeling through Extraction, Representation and Understanding of Medical Image Content (GALEN-POST), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Département d'Informatique et de Recherche Opérationnelle [Montreal] (DIRO), Université de Montréal (UdeM), Models of visual object recognition and scene understanding (WILLOW), Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria), ANR-16-CE23-0003,BoB,Inférence bayésienne à ressources limitées - données massives et modèles coûteux(2016), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Département d'informatique de l'École normale supérieure (DI-ENS), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), Université de Lille-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Département d'informatique - ENS Paris (DI-ENS), Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Inference, Machine Learning (stat.ML), 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, Convolutional neural network, Machine Learning (cs.LG), [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistics - Machine Learning, SIFT, 0202 electrical engineering, electronic engineering, information engineering, First-order scattering, Image resolution, 0105 earth and related environmental sciences, computer.programming_language, Image descriptors, Scattering, business.industry, Pattern recognition, Pascal (programming language), First order, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, CNN
Abstract

International audience; We study the first-order scattering transform as a candidate for reducing the signal processed by a convolutional neural network (CNN). We study this transformation and show theoretical and empirical evidence that in the case of natural images and sufficiently small translation invariance, this transform preserves most of the signal information needed for classification while substantially reducing the spatial resolution and total signal size. We show that cascading a CNN with this representation performs on par with ImageNet classification models commonly used in downstream tasks such as the ResNet-50. We subsequently apply our trained hybrid ImageNet model as a base model on a detection system, which has typically larger image inputs. On Pascal VOC and COCO detection tasks we deliver substantial improvements in the inference speed and training memory consumption compared to models trained directly on the input image.

Published
2018

3. Bandits attack function optimization

Author

Philippe Preux, Michal Valko, Rémi Munos, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), European Project: 270327,EC:FP7:ICT,FP7-ICT-2009-6,COMPLACS(2011), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Continuous optimization, Mathematical optimization, 021103 operations research, Meta-optimization, Optimization problem, 0211 other engineering and technologies, 02 engineering and technology, Multi-objective optimization, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Discrete optimization, 0202 electrical engineering, electronic engineering, information engineering, Random optimization, 020201 artificial intelligence & image processing, Global optimization, Metaheuristic, Mathematics
Abstract

International audience; We consider function optimization as a sequential decision making problem under the budget constraint. Such constraint limits the number of objective function evaluations allowed during the optimization. We consider an algorithm inspired by a continuous version of a multi-armed bandit problem which attacks this optimization problem by solving the tradeoff between exploration (initial quasi-uniform search of the domain) and exploitation (local optimization around the potentially global maxima). We introduce the so-called Simultaneous Optimistic Optimization (SOO), a deterministic algorithm that works by domain partitioning. The benefit of such an approach are the guarantees on the returned solution and the numerical eficiency of the algorithm. We present this machine learning rooted approach to optimization, and provide the empirical assessment of SOO on the CEC'2014 competition on single objective real-parameter numerical optimization testsuite.

Published
2014

4. Learning from a single labeled face and a stream of unlabeled data

Author

Michal Valko, Branislav Kveton, Technicolor [Cesson Sévigné], Technicolor, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), European Project: 270327,EC:FP7:ICT,FP7-ICT-2009-6,COMPLACS(2011), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Authentication, Contextual image classification, business.industry, Computer science, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, 02 engineering and technology, Semi-supervised learning, Machine learning, computer.software_genre, Facial recognition system, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], 020204 information systems, Personal computer, 0202 electrical engineering, electronic engineering, information engineering, False positive paradox, One-class classification, 020201 artificial intelligence & image processing, Artificial intelligence, False positive rate, business, computer
Abstract

International audience; Face recognition from a single image per person is a challenging problem because the training sample is extremely small. We consider a variation of this problem. In our problem, we recognize only one person, and there are no labeled data for any other person. This setting naturally arises in authentication on personal computers and mobile devices, and poses additional challenges because it lacks negative examples. We formalize our problem as one-class classification, and propose and analyze an algorithm that learns a non-parametric model of the face from a single labeled image and a stream of unlabeled data. In many domains, for instance when a person interacts with a computer with a camera, unlabeled data are abundant and easy to utilize. This is the first paper that investigates how these data can help in learning better models in the single-image-per-person setting. Our method is evaluated on a dataset of 43 people and we show that these people can be recognized 90% of time at nearly zero false positives. This recall is 25+% higher than the recall of our best performing baseline. Finally, we conduct a comprehensive sensitivity analysis of our algorithm and provide a guideline for setting its parameters in practice.

Published
2013
Full Text
View/download PDF

5. Outlier detection for patient monitoring and alerting

Author

Milos Hauskrecht, Iyad Batal, Gilles Clermont, Shyam Visweswaran, Gregory F. Cooper, Michal Valko, Department of Computer Science - University of Pittsburgh, University of Pittsburgh (PITT), Pennsylvania Commonwealth System of Higher Education (PCSHE)-Pennsylvania Commonwealth System of Higher Education (PCSHE), Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Department of Biomedical Informatics, Department of Critical Care Medicine, Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Conditional outlier detection, Medical Records Systems, Computerized, Remote patient monitoring, Health Informatics, 02 engineering and technology, Health records, computer.software_genre, Clinical alerting, Article, Patient care, 03 medical and health sciences, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Machine learning, 0202 electrical engineering, electronic engineering, information engineering, Medical errors, Humans, Medicine, Postoperative Period, 030212 general & internal medicine, health care economics and organizations, Monitoring, Physiologic, business.industry, 3. Good health, Computer Science Applications, Outlier, 020201 artificial intelligence & image processing, Anomaly detection, Data mining, business, computer, [SDV.MHEP]Life Sciences [q-bio]/Human health and pathology, Surgical patients
Abstract

International audience; We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management decisions using past patient cases stored in electronic health records (EHRs). Our hypothesis is that a patient-management decision that is unusual with respect to past patient care may be due to an error and that it is worthwhile to generate an alert if such a decision is encountered. We evaluate this hypothesis using data obtained from EHRs of 4486 post-cardiac surgical patients and a subset of 222 alerts generated from the data. We base the evaluation on the opinions of a panel of experts. The results of the study support our hypothesis that the outlier-based alerting can lead to promising true alert rates. We observed true alert rates that ranged from 25% to 66% for a variety of patient-management actions, with 66% corresponding to the strongest outliers.

Published
2013
Full Text
View/download PDF

6. Conditional Anomaly Detection with Soft Harmonic Functions

Author

Branislav Kveton, Milos Hauskrecht, Hamed Valizadegan, Michal Valko, Gregory F. Cooper, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Technicolor R & I [Cesson Sévigné], Technicolor, Department of Computer Science - University of Pittsburgh, University of Pittsburgh (PITT), Pennsylvania Commonwealth System of Higher Education (PCSHE)-Pennsylvania Commonwealth System of Higher Education (PCSHE), European Project: 270327,EC:FP7:ICT,FP7-ICT-2009-6,COMPLACS(2011), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Computer science, Boundary (topology), Harmonic (mathematics), 02 engineering and technology, computer.software_genre, Class (biology), Article, Distribution (mathematics), Harmonic function, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Anomaly detection, Data mining, computer, [SDV.MHEP]Life Sciences [q-bio]/Human health and pathology
Abstract

International audience; In this paper, we consider the problem of conditional anomaly detection that aims to identify data instances with an unusual response or a class label. We develop a new non-parametric approach for conditional anomaly detection based on the soft harmonic solution, with which we estimate the confidence of the label to detect anomalous mislabeling. We further regularize the solution to avoid the detection of isolated examples and examples on the boundary of the distribution support. We demonstrate the efficacy of the proposed method on several synthetic and UCI ML datasets in detecting unusual labels when compared to several baseline approaches. We also evaluate the performance of our method on a real-world electronic health record dataset where we seek to identify unusual patient-management decisions.

Published
2011

7. Online Semi-Supervised Perception: Real-Time Learning without Explicit Feedback

Author

Branislav Kveton, Michal Valko, Ling Huang, Matthai Philipose, Technicolor R & I [Cesson Sévigné], Technicolor, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), INTEL, Intel Research Seattle, Intel Research Laboratory, Intel, Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
Computer Science::Machine Learning, Computer science, media_common.quotation_subject, 02 engineering and technology, Machine learning, computer.software_genre, Facial recognition system, Computer graphics, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Robustness (computer science), 020204 information systems, Perception, 0202 electrical engineering, electronic engineering, information engineering, media_common, [STAT.AP]Statistics [stat]/Applications [stat.AP], business.industry, Quantization (signal processing), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Regret, Manifold, 020201 artificial intelligence & image processing, Algorithm design, Artificial intelligence, Precision and recall, business, computer
Abstract

International audience; This paper proposes an algorithm for real-time learning without explicit feedback. The algorithm combines the ideas of semi-supervised learning on graphs and online learning. In particular, it iteratively builds a graphical representation of its world and updates it with observed examples. Labeled examples constitute the initial bias of the algorithm and are provided offline, and a stream of unlabeled examples is collected online to update this bias. We motivate the algorithm, discuss how to implement it efficiently, prove a regret bound on the quality of its solutions, and apply it to the problem of real-time face recognition. Our recognizer runs in real time, and achieves superior precision and recall on 3 challenging video datasets.

Published
2010
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results