m
• E

F Nous contacter

0

# Documents  68T05 | enregistrements trouvés : 71

O

P Q

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Non-backtracking spectrum of random graphs: community detection and non-regular Ramanujan graphs Massoulié, Laurent | CIRM H

Post-edited

Research talks;Combinatorics;Computer Science;Probability and Statistics

A non-backtracking walk on a graph is a directed path such that no edge is the inverse of its preceding edge. The non-backtracking matrix of a graph is indexed by its directed edges and can be used to count non-backtracking walks of a given length. It has been used recently in the context of community detection and has appeared previously in connection with the Ihara zeta function and in some generalizations of Ramanujan graphs. In this work, we study the largest eigenvalues of the non-backtracking matrix of the Erdos-Renyi random graph and of the Stochastic Block Model in the regime where the number of edges is proportional to the number of vertices. Our results confirm the "spectral redemption" conjecture that community detection can be made on the basis of the leading eigenvectors above the feasibility threshold. A non-backtracking walk on a graph is a directed path such that no edge is the inverse of its preceding edge. The non-backtracking matrix of a graph is indexed by its directed edges and can be used to count non-backtracking walks of a given length. It has been used recently in the context of community detection and has appeared previously in connection with the Ihara zeta function and in some generalizations of Ramanujan graphs. In this work, we ...

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## L'informatique, de la révolution technique à la révolution mentale Berry, Gérard | CIRM H

Post-edited

Research talks;Computer Science

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Detection theory and novelty filters Morel, Jean-Michel | CIRM H

Post-edited

Research talks;Computer Science

In this presentation based on on-line demonstrations of algorithms and on the examination of several practical examples, I will reflect on the problem of modeling a detection task in images. I will place myself in the (very frequent) case where the detection task can not be formulated in a Bayesian framework or, rather equivalently that can not be solved by simultaneous learning of the model of the object and that of the background. (In the case where there are plenty of examples of the background and of the object to be detected, the neural networks provide a practical answer, but without explanatory power). Nevertheless for the detection without "learning", I will show that we can not avoid building a background model, or possibly learn it. But this will not require many examples.

Joint works with Axel Davy, Tristan Dagobert, Agnes Desolneux, Thibaud Ehret.
In this presentation based on on-line demonstrations of algorithms and on the examination of several practical examples, I will reflect on the problem of modeling a detection task in images. I will place myself in the (very frequent) case where the detection task can not be formulated in a Bayesian framework or, rather equivalently that can not be solved by simultaneous learning of the model of the object and that of the background. (In the case ...

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Expert systems and their applications. Vol. 29th international workshop general conference may 29 - june 2 9è journées internationales mai 29 - juin 2 | EC2 1989

Congrès

- Pp. 453-909
ISBN 978-0-904933-61-1

Localisation : Colloque 1er étage (AVIG)

application # contrôle # gestion # industrie des systèmes experts # intelligence artificielle # outil et technique de construction des systèmes experts # surveillance # système expert # système informatique # sécurité # télécommunication # économie des systèmes experts # électrotechnique

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Expert systems and their applications. Vol. 19th international workshop general conference May 29 - June 2 9è journées internationales mai 29 - juin 2 | EC2 1989

Congrès

- 449 p.
ISBN 978-0-904933-61-1

Localisation : Colloque 1er étage (AVIG)

application # contrôle # gestion # industrie des systèmes experts # intelligence artificielle # outil et technique de construction des systèmes experts # surveillance # système expert # système informatique # sécurité # télécommunication # économie des systèmes experts # électrotechnique

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Real-time computer vision Brown, Christopher M. ; Terzopoulos, Demetri | Cambridge University Press 1994

Congrès

ISBN 978-0-521-47278-4

Publications of the Newton Institut , 0004

Localisation : Colloque 1er étage (CAMB)

contrôle de comportement guidé visuellement # guidage de robot visuel à partir de stéréo non-calibrée # traquage et contrôle de voitures jouets # traquage visuel # vision et exploration basées sur un modèle # vision informatique en temps réel

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Eighth international conference on pattern recognition. Vol. 1proceedings of ... oct. 27-31 | IEEE Computer Society;IEEE Service Center 1986

Congrès

ISBN 978-0-8186-0742-4

Localisation : Colloque 1er étage (PARI)

algorithme # application biomédicale # architecture # automate # bord # classification des données # connaissance de base de reconnaissance de forme # inférence et apprentissage # limite # tomagraphie # traitement des images # traitement du signal # vision

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## IJCAI-93. Vol. 1Proceedings of the 13th international joint conference on artificial intelligence aug. 28 - sept. 3 | IJCAI 1993

Congrès

ISBN 978-1-55860-300-4

Localisation : Colloque 1er étage (CHAM)

AI distribuée # automate # automatique # intelligence artificielle # modèle co-positif # problème de satisfaction des contraintes # représentation des connaissances # système intelligent de Tutoring # technologie des connaissances de base

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Ijcai-93. vol. 2Proceedings of the 13th international joint conference on artificial intelligence. vol. 1 aug. 28 - sept. 3 | IJCAI 1993

Congrès

ISBN 978-1-55860-300-4

Localisation : Colloque 1er étage (CHAM)

apprentissage machine # langage naturel # paneau # panel # physique naive # planning # programmation logique # qualitatif # raisonnement # reseau neuronnaux # robotique et vision # vidéo # vision

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## On-line learning in neural networkspapers from the workshop held at the Isaac Newton Institute for mathematical sciences Nov. 17-21 Saad, David | Cambridge University Press 1998

Congrès

ISBN 978-0-521-65263-6

Publications of the newton institute

Localisation : Colloque 1er étage (CAMB)

analyse bayesienne # analyse de prototype en ligne # analyse en composante principale # analyse statistique # apprentissage # apprentissage en ligne # approximation stochastique # enseignement en ligne # réseau de neurone

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Eight international conference on pattern recognition. Vol. 2proceedings on ... Oct. 27-37 AFCET | IEEE Computer Society 1986

Congrès

ISBN 978-0-8186-0742-4

Localisation : Colloque 1er étage (PARI)

algorithme # application biomédicale # architecture # automate # bord # classification des données # connaissance de base de reconnaissance de forme # inférence et apprentissage # limite # tomographie # traitement des images # traitement du signal # vision

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Computational and experimental group theory :AMS-ASL joint special session interactions between logic, group theory and computer science#Janv. 15-16 Borovik, Alexandre V. ; Myasnikov, Alexei G. | American Mathematical Society 2004

Congrès

- 224 p.
ISBN 978-0-8218-3483-1

Contemporary mathematics , 0349

Localisation : Collection 1er étage

théorie des groupes # groupe de permutation # groupe non-abélien # théorie quantique # informatique # algorithme # groupe d'automorphisme # calcul quantique

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Soft computing and complex systemsworkshop on...#June 23-27 Quaresma, P. ; Dourado, A. ; Costa, E. | Centro Internacional de Matematica 2003

Congrès

- 132 p.

C.I.M. , 0021

Localisation : Colloque 1er étage (COIM)

système complexe # logique floue # réseau neuronal # calcul évolutif # complexité

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Graphs and discoveryproceedings of the DIMACS working group, computer-generated conjectures from graph theoretic and chemical databases and DIMACS public event, graph theory day 42Piscataway # november 10 and 12-16, 2001 Fajtlowicz, Siemion ; Fowler, Patrick W. ; Hansen, Pierre ; Janowitz, Melvin F. ; Roberts, Fred S. | American Mathematical Society 2005

Congrès

- xiv; 370 p.
ISBN 978-0-8218-4380-2

DIMACS series in discrete mathematics and theoretical computer science , 0069

Localisation : Collection 1er étage

combinatoires # informatique # chimie # graphe

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Algorithmic decision theory (ADT).Second international conference,Piscataway # October 2011 Brafman, Ronen I. ; Roberts, Fred S. ; Tsoukiàs, Alexis | Springer 2011

Congrès

- xi; 343 p.
ISBN 978-3-642-24872-6

Lecture notes in artificial intelligence , 6992

Localisation : Colloque 1er étage (PISC)

théorie de la décision # décision multicritère # informatique # programmation

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Data analysis, learning symbolic and numeric knowledge :proceedings of the conferenceAntibes # September 11-14, 1989 Diday, E. | Nova science publishers, Inc. 1989

Congrès

- xiii; 538 p.
ISBN 978-0-941743-64-8

Localisation : Colloque 1er étage (ANTI)

analyse multivariée # analyse factorielle # acquisition des connaissances # système expert # apprentissage automatique # ordinateur neuronal

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Comparative methods for RNA structure analysis - Part 1 Will, Sebastian | CIRM H

Multi angle

Research schools

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Individualized rank aggregation using nuclear norm regularization Neghaban, Sahand | CIRM

Multi angle

Research talks;Computer Science;Probability and Statistics

In recent years rank aggregation has received significant attention from the machine learning community. The goal of such a problem is to combine the (partially revealed) preferences over objects of a large population into a single, relatively consistent ordering of those objects. However, in many cases, we might not want a single ranking and instead opt for individual rankings. We study a version of the problem known as collaborative ranking. In this problem we assume that individual users provide us with pairwise preferences (for example purchasing one item over another). From those preferences we wish to obtain rankings on items that the users have not had an opportunity to explore. The results here have a very interesting connection to the standard matrix completion problem. We provide a theoretical justification for a nuclear norm regularized optimization procedure, and provide high-dimensional scaling results that show how the error in estimating user preferences behaves as the number of observations increase.

rank aggregation - nuclear norm - rank centrality - convex optimization - regularized $M$-estimation - matrix completion - collaborative filtering
In recent years rank aggregation has received significant attention from the machine learning community. The goal of such a problem is to combine the (partially revealed) preferences over objects of a large population into a single, relatively consistent ordering of those objects. However, in many cases, we might not want a single ranking and instead opt for individual rankings. We study a version of the problem known as collaborative ranking. ...

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Comparative methods for RNA structure analysis - Part 2 Will, Sebastian | CIRM H

Multi angle

Research schools

Déposez votre fichier ici pour le déplacer vers cet enregistrement.

## Large-scale machine learning and convex optimization 1/2 Bach, Francis | CIRM H

Multi angle

Research talks;Computer Science;Control Theory and Optimization;Probability and Statistics

Many machine learning and signal processing problems are traditionally cast as convex optimization problems. A common difficulty in solving these problems is the size of the data, where there are many observations ("large n") and each of these is large ("large p"). In this setting, online algorithms such as stochastic gradient descent which pass over the data only once, are usually preferred over batch algorithms, which require multiple passes over the data. Given n observations/iterations, the optimal convergence rates of these algorithms are $O(1/\sqrt{n})$ for general convex functions and reaches $O(1/n)$ for strongly-convex functions. In this tutorial, I will first present the classical results in stochastic approximation and relate them to classical optimization and statistics results. I will then show how the smoothness of loss functions may be used to design novel algorithms with improved behavior, both in theory and practice: in the ideal infinite-data setting, an efficient novel Newton-based stochastic approximation algorithm leads to a convergence rate of $O(1/n)$ without strong convexity assumptions, while in the practical finite-data setting, an appropriate combination of batch and online algorithms leads to unexpected behaviors, such as a linear convergence rate for strongly convex problems, with an iteration cost similar to stochastic gradient descent. Many machine learning and signal processing problems are traditionally cast as convex optimization problems. A common difficulty in solving these problems is the size of the data, where there are many observations ("large n") and each of these is large ("large p"). In this setting, online algorithms such as stochastic gradient descent which pass over the data only once, are usually preferred over batch algorithms, which require multiple passes ...

#### Filtrer

##### Codes MSC

Ressources Electroniques (Depuis le CIRM)

Books & Print journals

Recherche avancée

0
Z