Results 1  10
of
54
Recognizing Imprecisely Localized, Partially Occluded and Expression Variant Faces from a Single Sample per Class
, 2002
"... The classical way of attempting to solve the face (or object) recognition problem is by using large and representative datasets. In many applications though, only one sample per class is available to the system. In this contribution, we describe a probabilistic approach that is able to compensate fo ..."
Abstract

Cited by 147 (8 self)
 Add to MetaCart
The classical way of attempting to solve the face (or object) recognition problem is by using large and representative datasets. In many applications though, only one sample per class is available to the system. In this contribution, we describe a probabilistic approach that is able to compensate for imprecisely localized, partially occluded and expression variant faces even when only one single training sample per class is available to the system. To solve the localization problem, we find the subspace (within the feature space, e.g. eigenspace) that represents this error for each of the training images. To resolve the occlusion problem, each face is divided into k local regions which are analyzed in isolation. In contrast with other approaches, where a simple voting space is used, we present a probabilistic method that analyzes how "good" a local match is. To make the recognition system less sensitive to the differences between the facial expression displayed on the training and the testing images, we weight the results obtained on each local area on the bases of how much of this local area is affected by the expression displayed on the current test image.
Improving the Accuracy and Speed of Support Vector Machines
 Advances in Neural Information Processing Systems 9
, 1997
"... Support Vector Learning Machines (SVM) are finding application in pattern recognition, regression estimation, and operator inversion for illposed problems. Against this very general backdrop, any methods for improving the generalization performance, or for improving the speed in test phase, of SVMs ..."
Abstract

Cited by 144 (21 self)
 Add to MetaCart
Support Vector Learning Machines (SVM) are finding application in pattern recognition, regression estimation, and operator inversion for illposed problems. Against this very general backdrop, any methods for improving the generalization performance, or for improving the speed in test phase, of SVMs are of increasing interest. In this paper we combine two such techniques on a pattern recognition problem. The method for improving generalization performance (the "virtual support vector" method) does so by incorporating known invariances of the problem. This method achieves a drop in the error rate on 10,000 NIST test digit images of 1.4% to 1.0%. The method for improving the speed (the "reduced set" method) does so by approximating the support vector decision surface. We apply this method to achieve a factor of fifty speedup in test phase over the virtual support vector machine. The combined approach yields a machine which is both 22 times faster than the original machine, and which has ...
Is Learning The nth Thing Any Easier Than Learning The First?
 Advances in Neural Information Processing Systems
, 1996
"... This paper investigates learning in a lifelong context. Lifelong learning addresses situations in which a learner faces a whole stream of learning tasks. Such scenarios provide the opportunity to transfer knowledge across multiple learning tasks, in order to generalize more accurately from less trai ..."
Abstract

Cited by 138 (3 self)
 Add to MetaCart
This paper investigates learning in a lifelong context. Lifelong learning addresses situations in which a learner faces a whole stream of learning tasks. Such scenarios provide the opportunity to transfer knowledge across multiple learning tasks, in order to generalize more accurately from less training data. In this paper, several different approaches to lifelong learning are described, and applied in an object recognition domain. It is shown that across the board, lifelong learning approaches generalize consistently more accurately from less training data, by their ability to transfer knowledge across learning tasks. 1 Introduction Supervised learning is concerned with approximating an unknown function based on examples. Virtually all current approaches to supervised learning assume that one is given a set of inputoutput examples, denoted by X , which characterize an unknown function, denoted by f . The target function f is drawn from a class of functions, F , and the learner is gi...
ExplanationBased Neural Network Learning for Robot Control
 Advances in Neural Information Processing Systems 5
, 1993
"... How can artificial neural nets generalize better from fewer examples? In order to generalize successfully, neural network learning methods typically require large training data sets. We introduce a neural network learning method that generalizes rationally from many fewer data points, relying instea ..."
Abstract

Cited by 103 (25 self)
 Add to MetaCart
How can artificial neural nets generalize better from fewer examples? In order to generalize successfully, neural network learning methods typically require large training data sets. We introduce a neural network learning method that generalizes rationally from many fewer data points, relying instead on prior knowledge encoded in previously learned neural networks. For example, in robot control learning tasks reported here, previously learned networks that model the effects of robot actions are used to guide subsequent learning of robot control functions. For each observed training example of the target function (e.g. the robot control policy), the learner explains the observed example in terms of its prior knowledge, then analyzes this explanation to infer additional information about the shape, or slope, of the target function. This shape knowledge is used to bias generalization in the learned target function. Results are presented applying this approach to a simulated robot task bas...
Representation is Representation of Similarities
 Behavioral and Brain Sciences
, 1996
"... Advanced perceptual systems are faced with the problem of securing a principled relationship between the world and its internal representation. I propose a unified approach to visual representation, based on Shepard's (1968) notion of secondorder isomorphism. According to the proposed theory, a sha ..."
Abstract

Cited by 80 (18 self)
 Add to MetaCart
Advanced perceptual systems are faced with the problem of securing a principled relationship between the world and its internal representation. I propose a unified approach to visual representation, based on Shepard's (1968) notion of secondorder isomorphism. According to the proposed theory, a shape is represented internally by the responses of a few tuned modules, each of which is broadly selective for some reference shape, whose similarity to the stimulus it measures. The result is a philosophically appealing, computationally feasible, biologically credible, and formally veridical representation of a distal shape space. This approach supports representation of and discrimination among shapes radically different from the reference ones, while bypassing the need for the computationally problematic decomposition into parts; it also addresses the needs of shape categorization, and can be used to derive a range of models of perceived similarity. Representation is Representation of Sim...
Learning over Sets using Kernel Principal Angles
 Journal of Machine Learning Research
, 2003
"... We consider the problem of learning with instances defined over a space of sets of vectors. We derive a new positive definite kernel f (A,B) defined over pairs of matrices A,B based on the concept of principal angles between two linear subspaces. We show that the principal angles can be recovered ..."
Abstract

Cited by 79 (2 self)
 Add to MetaCart
We consider the problem of learning with instances defined over a space of sets of vectors. We derive a new positive definite kernel f (A,B) defined over pairs of matrices A,B based on the concept of principal angles between two linear subspaces. We show that the principal angles can be recovered using only innerproducts between pairs of column vectors of the input matrices thereby allowing the original column vectors of A,B to be mapped onto arbitrarily highdimensional feature spaces.
On a Kernelbased Method for Pattern Recognition, Regression, Approximation, and Operator Inversion
, 1997
"... We present a Kernelbased framework for Pattern Recognition, Regression Estimation, Function Approximation and multiple Operator Inversion. Previous approaches such as ridgeregression, Support Vector methods and regression by Smoothing Kernels are included as special cases. We will show connection ..."
Abstract

Cited by 77 (25 self)
 Add to MetaCart
We present a Kernelbased framework for Pattern Recognition, Regression Estimation, Function Approximation and multiple Operator Inversion. Previous approaches such as ridgeregression, Support Vector methods and regression by Smoothing Kernels are included as special cases. We will show connections between the costfunction and some properties up to now believed to apply to Support Vector Machines only. The optimal solution of all the problems described above can be found by solving a simple quadratic programming problem. The paper closes with a proof of the equivalence between Support Vector kernels and Greene's functions of regularization operators.
Learning One More Thing
, 1994
"... Most research on machine learning has focused on scenarios in which a learner faces a single, isolated learning task. The lifelong learning frameworkassumes instead that the learner encounters a multitude of related learning tasks over its lifetime, providing the opportunity for the transfer of know ..."
Abstract

Cited by 61 (6 self)
 Add to MetaCart
Most research on machine learning has focused on scenarios in which a learner faces a single, isolated learning task. The lifelong learning frameworkassumes instead that the learner encounters a multitude of related learning tasks over its lifetime, providing the opportunity for the transfer of knowledge. This paper studies lifelong learning in the context of binary classification. It presents the invariance approach, in which knowledge is transferred via a learned model of the invariances of the domain. Results on learning to recognize objects from color images demonstrate superior generalization capabilities if invariances are learned and used to bias subsequent learning. This research is sponsored in part by the National Science Foundation under award IRI9313367, and by the Wright Laboratory, Aeronautical Systems Center, Air Force Materiel Command, USAF, and the Advanced Research Projects Agency (ARPA) under grant number F336159311330. Views and conclusions contained in this doc...
Learning To Play the Game of Chess
 Advances in Neural Information Processing Systems 7
, 1995
"... This paper presents NeuroChess, a program which learns to play chess from the final outcome of games. NeuroChess learns chess board evaluation functions, represented by artificial neural networks. It integrates inductive neural network learning, temporal differencing, and a variant of explanationba ..."
Abstract

Cited by 58 (2 self)
 Add to MetaCart
This paper presents NeuroChess, a program which learns to play chess from the final outcome of games. NeuroChess learns chess board evaluation functions, represented by artificial neural networks. It integrates inductive neural network learning, temporal differencing, and a variant of explanationbased learning. Performance results illustrate some of the strengths and weaknesses of this approach. 1 Introduction Throughout the last decades, the game of chess has been a major testbed for research on artificial intelligence and computer science. Most of today's chess programs rely on intensive search to generate moves. To evaluate boards, fast evaluation functions are employed which are usually carefully designed by hand, sometimes augmented by automatic parameter tuning methods [1]. Building a chess machine that learns to play solely from the final outcome of games (win/loss/draw) is a challenging open problem in AI. In this paper, we are interested in learning to play chess from the fi...
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 56 (6 self)
 Add to MetaCart
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