Learning the 2-D Topology of Images
HAL (Le Centre pour la Communication Scientifique Directe)Published 3 December 2007
Nicolas Le Roux, Yoshua Bengio, Pascal Lamblin, Marc Joliveau, Balázs Kégl
Citations16
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The surprising result presented here is that about as few as a thousand images are enough to approximately recover the relative locations of about a thousand pixels.
Abstract
International audience
Keywords
Computer ScienceEngineering
Proceedings of the IEEEGradient-based learning applied to document recognition
58,219 Citations1998Yann LeCun, Léon Bottou +2 more
This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.
International Journal of Computer VisionDistinctive Image Features from Scale-Invariant Keypoints
55,266 Citations2004David Lowe
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
ScienceNonlinear Dimensionality Reduction by Locally Linear Embedding
15,035 Citations2000Sam T. Roweis, Lawrence K. Saul
Locally linear embedding (LLE) is introduced, an unsupervised learning algorithm that computes low-dimensional, neighborhood-preserving embeddings of high-dimensional inputs that learns the global structure of nonlinear manifolds.
ScienceA Global Geometric Framework for Nonlinear Dimensionality Reduction
13,740 Citations2000Joshua B. Tenenbaum, Vin de Silva +1 more
An approach to solving dimensionality reduction problems that uses easily measured local metric information to learn the underlying global geometry of a data set and efficiently computes a globally optimal solution, and is guaranteed to converge asymptotically to the true structure.
Neural ComputationBackpropagation Applied to Handwritten Zip Code Recognition
11,878 Citations1989Yann LeCun, Bernhard E. Boser +5 more
This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
IEEE Transactions on Speech and Audio ProcessingMusical genre classification of audio signals
2,777 Citations2002George Tzanetakis, Patrick Cook
The automatic classification of audio signals into an hierarchy of musical genres is explored and three feature sets for representing timbral texture, rhythmic content and pitch content are proposed.
Information science and statisticsEstimation of Dependences Based on Empirical Data
2,238 Citations2006Vladimir Vapnik
Scaling learning algorithms towards AI
927 Citations2007Yoshua Bengio, Yann LeCun
It is argued that deep architectures have the potential to generalize in non-local ways, i.e., beyond immediate neighbors, and that this is crucial in order to make progress on the kind of complex tasks required for artificial intelligence.
The MIT Press eBooksLarge-Scale Kernel Machines
542 Citations2007
This volume offers researchers and engineers practical solutions for learning from large scale datasets, with detailed descriptions of algorithms and experiments carried out on realistically large datasets, and offers information that can address the relative lack of theoretical grounding for many useful algorithms.
Neural ComputationTopographic Independent Component Analysis
466 Citations2001Aapo Hyvärinen, Patrik O. Hoyer +1 more
A linear decomposition is obtained into approximately independent components, where the dependence of two components is approximated by the proximity of the components in the topographic representation.
The MIT Press eBooksScaling Learning Algorithms toward AI
430 Citations2007Yoshua Bengio, Yann LeCun
This chapter contains sections titled: Introduction, LearningModels Toward AI, Learning Architectures, Shallow and Deep, Fundamental Limitation of Local Learning, Deep Architecture, Experiments with Visual Pattern Recognition, Conclusion.
Neural ComputationModular Construction of Time-Delay Neural Networks for Speech Recognition
320 Citations1989Alex Waibel
It is shown that small networks trained to perform limited tasks develop time invariant, hidden abstractions that can be exploited to train larger, more complex nets efficiently, and phoneme recognition networks of increasing complexity can be constructed that all achieve superior recognition performance.
An introduction to nonlinear dimensionality reduction by maximum variance unfolding
247 Citations2006Killan Q. Weinberger, Lawrence K. Saul
A recently proposed algorithm-- maximum, variance unfolding--for learning faithful low dimensional representations of high dimensional data, which relies on modem tools in convex optimization that are proving increasingly useful in many areas of machine learning.
IEEE Transactions on Image ProcessingUnsupervised image classification, segmentation, and enhancement using ICA mixture models
122 Citations2002Te-Won Lee, Michael S. Lewicki
This paper demonstrates that the unsupervised classification method, derived by modeling observed data as a mixture of several mutually exclusive classes that are each described by linear combinations of independent, non-Gaussian densities, was effective in classifying complex image textures such as natural scenes and text.
Neural ComputationTopographic Product Models Applied to Natural Scene Statistics
107 Citations2005Simon Osindero, Max Welling +1 more
An energy-based model is presented that uses a product of generalized Student-t distributions to capture the statistical structure in data sets to study the topographic organization of Gabor-like receptive fields that the model learns.
A New View of ICA
13 Citations2001GE Hinton, Max Welling +2 more
A new way of interpreting ICA as a probability density model and anew way of fitting this model to data are presented, which suggests different generalizations of the basic ICA algorithm which preserve the computationally attractive property that the hidden activities are a simple deterministic function of the observed data.