Results 1  10
of
42
Independent Component Analysis
 Neural Computing Surveys
, 2001
"... A common problem encountered in such disciplines as statistics, data analysis, signal processing, and neural network research, is nding a suitable representation of multivariate data. For computational and conceptual simplicity, such a representation is often sought as a linear transformation of the ..."
Abstract

Cited by 1550 (93 self)
 Add to MetaCart
A common problem encountered in such disciplines as statistics, data analysis, signal processing, and neural network research, is nding a suitable representation of multivariate data. For computational and conceptual simplicity, such a representation is often sought as a linear transformation of the original data. Wellknown linear transformation methods include, for example, principal component analysis, factor analysis, and projection pursuit. A recently developed linear transformation method is independent component analysis (ICA), in which the desired representation is the one that minimizes the statistical dependence of the components of the representation. Such a representation seems to capture the essential structure of the data in many applications. In this paper, we survey the existing theory and methods for ICA. 1
Fast and robust fixedpoint algorithms for independent component analysis
 IEEE TRANS. NEURAL NETW
, 1999
"... Independent component analysis (ICA) is a statistical method for transforming an observed multidimensional random vector into components that are statistically as independent from each other as possible. In this paper, we use a combination of two different approaches for linear ICA: Comon’s informat ..."
Abstract

Cited by 535 (34 self)
 Add to MetaCart
Independent component analysis (ICA) is a statistical method for transforming an observed multidimensional random vector into components that are statistically as independent from each other as possible. In this paper, we use a combination of two different approaches for linear ICA: Comon’s informationtheoretic approach and the projection pursuit approach. Using maximum entropy approximations of differential entropy, we introduce a family of new contrast (objective) functions for ICA. These contrast functions enable both the estimation of the whole decomposition by minimizing mutual information, and estimation of individual independent components as projection pursuit directions. The statistical properties of the estimators based on such contrast functions are analyzed under the assumption of the linear mixture model, and it is shown how to choose contrast functions that are robust and/or of minimum variance. Finally, we introduce simple fixedpoint algorithms for practical optimization of the contrast functions. These algorithms optimize the contrast functions very fast and reliably.
Learning lowlevel vision
 International Journal of Computer Vision
, 2000
"... We show a learningbased method for lowlevel vision problems. We setup a Markov network of patches of the image and the underlying scene. A factorization approximation allows us to easily learn the parameters of the Markov network from synthetic examples of image/scene pairs, and to e ciently prop ..."
Abstract

Cited by 474 (25 self)
 Add to MetaCart
We show a learningbased method for lowlevel vision problems. We setup a Markov network of patches of the image and the underlying scene. A factorization approximation allows us to easily learn the parameters of the Markov network from synthetic examples of image/scene pairs, and to e ciently propagate image information. Monte Carlo simulations justify this approximation. We apply this to the \superresolution &quot; problem (estimating high frequency details from a lowresolution image), showing good results. For the motion estimation problem, we show resolution of the aperture problem and llingin arising from application of the same probabilistic machinery.
A fast fixedpoint algorithm for independent component analysis
 Neural Computation
, 1997
"... Abstract. Independent Subspace Analysis (ISA; Hyvarinen & Hoyer, 2000) is an extension of ICA. In ISA, the components are divided into subspaces and components in different subspaces are assumed independent, whereas components in the same subspace have dependencies.In this paper we describe a fi ..."
Abstract

Cited by 447 (19 self)
 Add to MetaCart
Abstract. Independent Subspace Analysis (ISA; Hyvarinen & Hoyer, 2000) is an extension of ICA. In ISA, the components are divided into subspaces and components in different subspaces are assumed independent, whereas components in the same subspace have dependencies.In this paper we describe a fixedpoint algorithm for ISA estimation, formulated in analogy to FastICA. In particular we give a proof of the quadratic convergence of the algorithm, and present simulations that confirm the fast convergence, but also show that the method is prone to convergence to local minima. 1
Emergence of Phase and ShiftInvariant Features by Decomposition of Natural Images into Independent Feature Subspaces
, 2000
"... this article, we show that the same principle of independence maximization can explain the emergence of phase and shiftinvariant features, similar to those found in complex cells. This new kind of emergence is obtained by maximizing the independence between norms of projections on linear subspaces ..."
Abstract

Cited by 168 (31 self)
 Add to MetaCart
this article, we show that the same principle of independence maximization can explain the emergence of phase and shiftinvariant features, similar to those found in complex cells. This new kind of emergence is obtained by maximizing the independence between norms of projections on linear subspaces (instead of the independence of simple linear filter outputs). Thenorms of the projections on such "independent feature subspaces" then indicate the values of invariant features
Learning multiple layers of features from tiny images
, 2009
"... April 8, 2009Groups at MIT and NYU have collected a dataset of millions of tiny colour images from the web. It is, in principle, an excellent dataset for unsupervised training of deep generative models, but previous researchers who have tried this have found it di cult to learn a good set of lters f ..."
Abstract

Cited by 110 (5 self)
 Add to MetaCart
April 8, 2009Groups at MIT and NYU have collected a dataset of millions of tiny colour images from the web. It is, in principle, an excellent dataset for unsupervised training of deep generative models, but previous researchers who have tried this have found it di cult to learn a good set of lters from the images. We show how to train a multilayer generative model that learns to extract meaningful features which resemble those found in the human visual cortex. Using a novel parallelization algorithm to distribute the work among multiple machines connected on a network, we show how training such a model can be done in reasonable time. A second problematic aspect of the tiny images dataset is that there are no reliable class labels which makes it hard to use for object recognition experiments. We created two sets of reliable labels. The CIFAR10 set has 6000 examples of each of 10 classes and the CIFAR100 set has 600 examples of each of 100 nonoverlapping classes. Using these labels, we show that object recognition is signi cantly
Sparse Code Shrinkage: Denoising of Nongaussian Data by Maximum Likelihood Estimation
, 1999
"... Sparse coding is a method for finding a representation of data in which each of the components of the representation is only rarely significantly active. Such a representation is closely related to redundancy reduction and independent component analysis, and has some neurophysiological plausibility. ..."
Abstract

Cited by 92 (14 self)
 Add to MetaCart
Sparse coding is a method for finding a representation of data in which each of the components of the representation is only rarely significantly active. Such a representation is closely related to redundancy reduction and independent component analysis, and has some neurophysiological plausibility. In this paper, we show how sparse coding can be used for denoising. Using maximum likelihood estimation of nongaussian variables corrupted by gaussian noise, we show how to apply a softthresholding (shrinkage) operator on the components of sparse coding so as to reduce noise. Our method is closely related to the method of wavelet shrinkage, but it has the important benefit over wavelet methods that the representation is determined solely by the statistical properties of the data. The wavelet representation, on the other hand, relies heavily on certain mathematical properties (like selfsimilarity) that may be only weakly related to the properties of natural data.
A TwoLayer Sparse Coding Model Learns Simple and Complex Cell Receptive Fields and Topography From Natural Images
 VISION RESEARCH
, 2001
"... The classical receptive fields of simple cells in the visual cortex have been shown to emerge from the statistical properties of natural images by forcing the cell responses to be maximally sparse, i.e. significantly activated only rarely. Here, we show that this single principle of sparseness can ..."
Abstract

Cited by 69 (17 self)
 Add to MetaCart
The classical receptive fields of simple cells in the visual cortex have been shown to emerge from the statistical properties of natural images by forcing the cell responses to be maximally sparse, i.e. significantly activated only rarely. Here, we show that this single principle of sparseness can also lead to emergence of topography (columnar organization) and complex cell properties as well. These are obtained by maximizing the sparsenesses of locally pooled energies, which correspond to complex cell outputs. Thus we obtain a highly parsimonious model of how these properties of the visual cortex are adapted to the characteristics of the natural input.
Learning to estimate scenes from images
 Adv. Neural Information Processing Systems 11
, 1999
"... We seek the scene interpretation that best explains image data. ..."
Abstract

Cited by 37 (6 self)
 Add to MetaCart
We seek the scene interpretation that best explains image data.
Independent component analysis in the presence of gaussian noise by maximizing joint likelihood
 Neurocomputing
, 1998
"... We consider the estimation of the data model of independent component analysis when gaussian noise is present. We show that the joint maximum likelihood estimation of the independent components and the mixing matrix leads to an objective function already proposed by Olshausen and Field using a di er ..."
Abstract

Cited by 32 (3 self)
 Add to MetaCart
We consider the estimation of the data model of independent component analysis when gaussian noise is present. We show that the joint maximum likelihood estimation of the independent components and the mixing matrix leads to an objective function already proposed by Olshausen and Field using a di erent derivation. Due to the complicated nature of the objective function, we introduce approximations that greatly simplify the optimization problem. We show that the presence of noise implies that the relation between the observed data and the estimates of the independent components is nonlinear, and show how to approximate this nonlinearity. In particular, the nonlinearity may be approximated by a simple shrinkage operation in the case of supergaussian (sparse) data. Using these approximations, we propose an e cient algorithm for approximate maximization of the likelihood. In the case of supergaussian components, this may be approximated by simple competitive learning, and in the case of subgaussian components, by anticompetitive learning. Key words: Independent component analysis, blind source separation, maximum likelihood, competitive learning, neural networks. 1