Results 1  10
of
111
Learning Deep Architectures for AI
"... Theoretical results suggest that in order to learn the kind of complicated functions that can represent highlevel abstractions (e.g. in vision, language, and other AIlevel tasks), one may need deep architectures. Deep architectures are composed of multiple levels of nonlinear operations, such as i ..."
Abstract

Cited by 183 (32 self)
 Add to MetaCart
Theoretical results suggest that in order to learn the kind of complicated functions that can represent highlevel abstractions (e.g. in vision, language, and other AIlevel tasks), one may need deep architectures. Deep architectures are composed of multiple levels of nonlinear operations, such as in neural nets with many hidden layers or in complicated propositional formulae reusing many subformulae. Searching the parameter space of deep architectures is a difficult task, but learning algorithms such as those for Deep Belief Networks have recently been proposed to tackle this problem with notable success, beating the stateoftheart in certain areas. This paper discusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of singlelayer models such as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks.
Representation Learning: A Review and New Perspectives
, 2012
"... The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to ..."
Abstract

Cited by 153 (4 self)
 Add to MetaCart
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representationlearning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and joint training of deep learning, covering advances in probabilistic models, autoencoders, manifold learning, and deep architectures. This motivates longerterm unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.
Dimension Reduction by Local Principal Component Analysis
, 1997
"... Reducing or eliminating statistical redundancy between the components of highdimensional vector data enables a lowerdimensional representation without significant loss of information. Recognizing the limitations of principal component analysis (PCA), researchers in the statistics and neural networ ..."
Abstract

Cited by 130 (0 self)
 Add to MetaCart
Reducing or eliminating statistical redundancy between the components of highdimensional vector data enables a lowerdimensional representation without significant loss of information. Recognizing the limitations of principal component analysis (PCA), researchers in the statistics and neural network communities have developed nonlinear extensions of PCA. This article develops a local linear approach to dimension reduction that provides accurate representations and is fast to compute. We exercise the algorithms on speech and image data, and compare performance with PCA and with neural network implementations of nonlinear PCA. We find that both nonlinear techniques can provide more accurate representations than PCA and show that the local linear techniques outperform neural network implementations.
A first application of independent component analysis to extracting structure from stock returns
 International Journal of Neural Systems
, 1997
"... ..."
Recognizing handwritten digits using mixtures of linear models
 Advances in Neural Information Processing Systems 7
, 1995
"... We construct a mixture of locally linear generative models of a collection of pixelbased images of digits, and use them for recognition. Different models of a given digit are used to capture different styles of writing, and new images are classified by evaluating their loglikelihoods under each mo ..."
Abstract

Cited by 64 (6 self)
 Add to MetaCart
(Show Context)
We construct a mixture of locally linear generative models of a collection of pixelbased images of digits, and use them for recognition. Different models of a given digit are used to capture different styles of writing, and new images are classified by evaluating their loglikelihoods under each model. We use an EMbased algorithm in which the Mstep is computationally straightforward principal components analysis (PCA). Incorporating tangentplane information [12] about expected local deformations only requires adding tangent vectors into the sample covariance matrices for the PCA, and it demonstrably improves performance. 1
Learning in Linear Neural Networks: a Survey
 IEEE Transactions on neural networks
, 1995
"... Networks of linear units are the simplest kind of networks, where the basic questions related to learning, generalization, and selforganisation can sometimes be answered analytically. We survey most of the known results on linear networks, including: (1) backpropagation learning and the structure ..."
Abstract

Cited by 61 (5 self)
 Add to MetaCart
(Show Context)
Networks of linear units are the simplest kind of networks, where the basic questions related to learning, generalization, and selforganisation can sometimes be answered analytically. We survey most of the known results on linear networks, including: (1) backpropagation learning and the structure of the error function landscape; (2) the temporal evolution of generalization; (3) unsupervised learning algorithms and their properties. The connections to classical statistical ideas, such as principal component analysis (PCA), are emphasized as well as several simple but challenging open questions. A few new results are also spread across the paper, including an analysis of the effect of noise on backpropagation networks and a unified view of all unsupervised algorithms. Keywords linear networks, supervised and unsupervised learning, Hebbian learning, principal components, generalization, local minima, selforganisation I. Introduction This paper addresses the problems of supervise...
Fast nonlinear dimension reduction
 In IEEE International Conference on Neural Networks
, 1993
"... We present a fast algorithm for nonlinear dimension reduction. The algorithm builds a local linear model of the data by merging PCA with clustering based on a new distortion measure. Experiments with speech and image data indicate that the local linear algorithm produces encodings with lower distor ..."
Abstract

Cited by 57 (5 self)
 Add to MetaCart
(Show Context)
We present a fast algorithm for nonlinear dimension reduction. The algorithm builds a local linear model of the data by merging PCA with clustering based on a new distortion measure. Experiments with speech and image data indicate that the local linear algorithm produces encodings with lower distortion than those built by velayer autoassociative networks. The local linear algorithm is also more than an order of magnitude faster to train. 1
A review of dimension reduction techniques
, 1997
"... The problem of dimension reduction is introduced as a way to overcome the curse of the dimensionality when dealing with vector data in highdimensional spaces and as a modelling tool for such data. It is defined as the search for a lowdimensional manifold that embeds the highdimensional data. A cl ..."
Abstract

Cited by 42 (4 self)
 Add to MetaCart
(Show Context)
The problem of dimension reduction is introduced as a way to overcome the curse of the dimensionality when dealing with vector data in highdimensional spaces and as a modelling tool for such data. It is defined as the search for a lowdimensional manifold that embeds the highdimensional data. A classification of dimension reduction problems is proposed. A survey of several techniques for dimension reduction is given, including principal component analysis, projection pursuit and projection pursuit regression, principal curves and methods based on topologically continuous maps, such as Kohonen’s maps or the generalised topographic mapping. Neural network implementations for several of these techniques are also reviewed, such as the projection pursuit learning network and the BCM neuron with an objective function. Several appendices complement the mathematical treatment of the main text.
An optimality principle for unsupervised learning
 in Advances in Neural Information Processing
, 1989
"... We propose an optimality principle for training an unsupervised feedforward neural network based upon maximal ability to reconstruct the input data from the network outputs. We describe an algorithm which can be used to train either linear or nonlinear networks with certain types of nonlinearity. ..."
Abstract

Cited by 35 (1 self)
 Add to MetaCart
(Show Context)
We propose an optimality principle for training an unsupervised feedforward neural network based upon maximal ability to reconstruct the input data from the network outputs. We describe an algorithm which can be used to train either linear or nonlinear networks with certain types of nonlinearity. Examples of applications to the problems of image coding, feature detection, and analysis of randomdot stereograms are presented. 1.