WorldCat Identities

LeCun, Yann

Overview
Works: 30 works in 45 publications in 2 languages and 589 library holdings
Genres: Conference papers and proceedings  Academic theses  Periodicals 
Roles: Author of introduction, Author, Thesis advisor, Interviewee
Classifications: QP363.3, 006.3
Publication Timeline
.
Most widely held works by Yann LeCun
2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition : CVPR 2006 : proceedings : June 17-22, 2006, New York, NY by IEEE Computer Society Conference on Computer Vision and Pattern Recognition( )

4 editions published in 2006 in English and held by 227 WorldCat member libraries worldwide

Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop : (CVPRW'06) : [June 17-22, 2006, New York, NY by IEEE Computer Society Conference on Computer Vision and Pattern Recognition( )

2 editions published in 2006 in English and held by 195 WorldCat member libraries worldwide

IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006 CVPR 2006 ; June 17-22, 2006, New York, NY ; proceedings( )

1 edition published in 2006 in English and held by 34 WorldCat member libraries worldwide

Advances in neural information processing systems : proceedings of the first 12 conferences by Neural Information Processing Systems( Book )

2 editions published in 2001 in English and held by 24 WorldCat member libraries worldwide

Contains the entire proceedings of the 12 Neural Information Processing Systems conferences from 1988 to 1999
Data science : fondamentaux et études de cas : machine learning avec Python et R by Éric Biernat( )

1 edition published in 2015 in French and held by 22 WorldCat member libraries worldwide

Reassessing FHA risk by Diego Aragon( Book )

3 editions published in 2010 in English and held by 11 WorldCat member libraries worldwide

Abstract: Federal Housing Administration (FHA) insurance has doubled over the past two years and is projected to redouble to $1.5 trillion over the next five. Despite clear signs of strain in the FHA's Mutual Mortgage Insurance Fund, a recent actuarial review indicates that the FHA will not need any form of government support. We identify four risk factors that make such a funding request more likely; the review underestimates how many FHA borrowers are underwater and in economic distress; it uses measures of house values that lower loss estimates; it does not incorporate early-warning signals of future losses that are available from mortgage delinquency; and it ignores potential risks associated with recent down-payment assistant programs despite higher losses on previous programs of this type. We propose measures that could be taken to improve the predictive accuracy of FHA risk assessment
La plus belle histoire de l'intelligence : des origines aux neurones artificiels : vers une nouvelle étape de l'évolution by Stanislas Dehaene( Book )

3 editions published in 2018 in French and held by 9 WorldCat member libraries worldwide

Les auteurs retracent l'histoire de l'intelligence, qui a émergé dans la nuit des temps, s'est développée au fil de l'évolution et s'est magnifiée avec l'espèce humaine. Ils s'interrogent sur son futur, se demandant par exemple si l'art, la beauté ou la capacité de se connaître soi-même sont à la portée de cerveaux immatériels. [Electre]
Proceedings 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, June 17-22, 2006, New York, NY by Conference on Computer Vision and Pattern Recognition( Book )

2 editions published in 2006 in English and held by 8 WorldCat member libraries worldwide

Advances in neural information processing systems by Neural Information Processing Systems (Conference)( Book )

1 edition published in 2001 in English and held by 7 WorldCat member libraries worldwide

Contains the entire proceedings of the twelve neural information processing system conferences from 1988 to 1999. Includes free browsers for all major platforms
Modèles connexionnistes de l'apprentissage by Yann LeCun( Book )

4 editions published in 1987 in French and held by 7 WorldCat member libraries worldwide

Etude des modèles d'apprentissage simples et application aux mémoires associatives. Méthodes d'apprentissage pour réseaux à cellules cachées. Algorithme de retro propagation et ses variantes. Applications diverses (associative, reconnaissance de caractères, diagnostic médical) et logiciel de simulation
Uncovering spatio-temporal patterns in Los Angeles house prices: New data, new methods, new findings by Trivikraman Thampy( )

1 edition published in 2008 in English and held by 4 WorldCat member libraries worldwide

The goal of the thesis is to move forward scientific understanding of house prices. The critical challenge lies in the massive data involved in understanding house price dynamics. There have been very few studies published using anything like the full volume of collected data, and the analysis that have been conducted have largely been rudimentary, given that economists have less experience with these massive data sets than do computer scientists. My Ph. D thesis represents the most complete effort to join intellectual resources with computer scientists that has yet been undertaken in the literature on house prices, and possibly in the broader economic literature
Advances in neural information processing systems : proceedings of the first 12 conferences by Neural Information Processing Systems (Conference)( )

2 editions published in 2001 in English and held by 4 WorldCat member libraries worldwide

Learning Hierarchical Feature Extractors For Image Recognition by Y-Lan Boureau( )

1 edition published in 2012 in English and held by 3 WorldCat member libraries worldwide

Telling cow from sheep is effortless for most animals, but requires much engineering for computers. In this thesis, we seek to tease out basic principles that underlie many recent advances in image recognition. First, we recast many methods into a common unsupervised feature extraction framework based on an alternation of coding steps, which encode the input by comparing it with a collection of reference patterns, and pooling steps, which compute an aggregation statistic summarizing the codes within some region of interest of the image. Within that framework, we conduct extensive comparative evaluations of many coding or pooling operators proposed in the literature. Our results demonstrate a robust superiority of sparse coding (which decomposes an input as a linear combination of a few visual words) and max pooling (which summarizes a set of inputs by their maximum value). We also propose macrofeatures, which import into the popular spatial pyramid framework the joint encoding of nearby features commonly practiced in neural networks, and obtain significantly improved image recognition performance. Next, we analyze the statistical properties of max pooling that underlie its better performance, through a simple theoretical model of feature activation. We then present results of experiments that confirm many predictions of the model. Beyond the pooling operator itself, an important parameter is the set of pools over which the summary statistic is computed. We propose locality in feature configuration space as a natural criterion for devising better pools. Finally, we propose ways to make coding faster and more powerful through fast convolutional feedforward architectures, and examine how to incorporate supervision into feature extraction schemes. Overall, our experiments offer insights into what makes current systems work so well, and state-of-the-art results on several image recognition benchmarks
Time series modeling with hidden variables and gradient-based algorithms by Piotr Mirowski( )

1 edition published in 2011 in English and held by 3 WorldCat member libraries worldwide

To address this problem, I have developed tractable, gradient-based methods for training Dynamic Factor Graphs (DFG) with continuous latent variables. DFGs consist of (potentially highly nonlinear) factors modeling joint probabilities between hidden and observed variables. My hypothesis is that a principled inference of hidden variables is achievable in the energy-based framework, through gradient-based optimization to find the minimum-energy state sequence given observations. This enables higher-order nonlinearities than graphical models. Maximum likelihood learning is done by minimizing the expected energy over training sequences with respect to the factors' parameters. These alternated inference and parameter updates constitute a deterministic EM-like procedure
Continuous basis pursuit and its applications by Chaitanya Ekanadham( )

1 edition published in 2012 in English and held by 3 WorldCat member libraries worldwide

Transformation-invariance is a major source of nonlinear structure in many real signal ensembles. To model this structure, we develop a methodology for decomposing a signal into a sparse linear combination of continuously transformed features. The central idea is to approximate the manifold(s) of transformed features(s) by linearly combining interpolation functions using constrained coefficients that can be recovered via convex programming. The advantage of this approach over traditional sparse coding methods is threefold: (1) it is built upon a more accurate probabilistic source model for transformation-invariant ensembles, (2) it uses a more efficient dictionary, and (3) both structural and transformational information can be extracted separately from the representation via well-defined mappings, providing transformation-invariant and -equivariant information, respectively
Numerical estimation of the second largest eigenvalue of a reversible Markov transition matrix by Kranthi Kumar Gade( )

1 edition published in 2008 in English and held by 3 WorldCat member libraries worldwide

We discuss the problem of finding the second largest eigenvalue of an operator that defines a reversible Markov chain. The second largest eigenvalue governs the rate at which the statistics of the Markov chain converge to equilibrium. Scientific applications include understanding the very slow dynamics of some models of dynamic glass. Applications in computing include estimating the rate of convergence of Markov chain Monte Carlo algorithms
Flexible-Cost SLAM by Matthew Koichi Grimes( )

1 edition published in 2012 in English and held by 3 WorldCat member libraries worldwide

The ability of a robot to track its position and its surroundings is critical in mobile robotics applications, such as autonomous transport, farming, search-and-rescue, and planetary exploration
Factor graphs for relational regression by Sumit Prakash Chopra( )

1 edition published in 2008 in English and held by 3 WorldCat member libraries worldwide

The models are applied to predicting the prices of real estate properties. A by-product of it is a house price index. The relational aspect of the model accounts for the hidden spatio-temporal influences on the price of every house. The experiments show that one can achieve considerably superior performance by identifying and using the underlying spatio-temporal structure associated with the problem. To the best of our knowledge this is the first work in the direction of relational regression, especially in the frame-based class of statistical relational learning models. Furthermore, this is also the first work in constructing house price indices by simultaneously accounting for the spatio-temporal effects on house prices using large-scale industry standard data set
Semi-supervised Learning via Generalized Maximum Entropy by Ayse Naz Erkan( )

1 edition published in 2010 in English and held by 3 WorldCat member libraries worldwide

The maximum entropy (MaxEnt) framework has been studied extensively in the supervised setting. Here, the goal is to find a distribution p that maximizes an entropy function while enforcing data constraints so that the expected values of some (pre-defined) features with respect to p match their empirical counterparts approximately. Using different entropy measures, different model spaces for p, and different approximation criteria for the data constraints, yields a family of discriminative supervised learning methods (e.g., logistic regression, conditional random fields, least squares and boosting) (Dudik & Schapire, 2006; Friedlander & Gupta, 2006; Altun & Smola, 2006). This framework is known as the generalized maximum entropy framework
Building an automatic phenotyping system of developing embryos by Feng Ning( )

1 edition published in 2006 in English and held by 3 WorldCat member libraries worldwide

Our study primarily concerns the early stages of development of C. Elegans nematode embryos, from fertilization to the four-cell stage. The method proposed in this dissertation consists in learning the entire processing chain from end to end, from raw pixels to ultimate object categories
 
moreShow More Titles
fewerShow Fewer Titles
Audience Level
0
Audience Level
1
  Kids General Special  
Audience level: 0.58 (from 0.50 for Proceeding ... to 0.94 for Proceeding ...)

Advances in neural information processing systems : proceedings of the first 12 conferences Advances in neural information processing systems Advances in neural information processing systems : proceedings of the first 12 conferences
Covers
Advances in neural information processing systemsAdvances in neural information processing systems : proceedings of the first 12 conferences
Alternative Names
Yann LeCun computer scientist working in machine learning and computer vision

Yann LeCun Frans informaticus

Yann LeCun fransk ingeniør og informatikar

Yann LeCun fransk ingeniør og informatiker

Yann LeCun fransk ingenjör och datavetare

Ян ЛеКун

Languages
English (26)

French (8)