Results 1 
6 of
6
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 511 (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.
Feature Centrality and Conceptual Coherence
 Cognitive Science
, 1998
"... This paper has two objectives. First, we will argue that the mutability of conceptual fea tures can be represented as a single, multiplevalued dimension. We will show that the fea tures of a concept can be reliably ordered with respect to the degree to which people are willing to transform the fe ..."
Abstract

Cited by 59 (6 self)
 Add to MetaCart
This paper has two objectives. First, we will argue that the mutability of conceptual fea tures can be represented as a single, multiplevalued dimension. We will show that the fea tures of a concept can be reliably ordered with respect to the degree to which people are willing to transform the feature while retaining the integrity of a representation; i.e., that a number of conceptual tasks, all of which require people to transform conceptual features, produce similar orderings. Following Medin and Shoben (1988), these tasks have in common that they ask people to consider an object that is missing a feature but is otherwise intact (e.g., a real chair without a seat)
THE EFFECTS OF DIFFERENT TYPES OF FACTOR ANALYSIS ON ERROR REDUCTION 23 THE EFFECTS OF DIFFERENT TYPES OF FACTOR ANALYSIS ON ERROR REDUCTION
"... Computer Information Systems This study demonstrates that a commonly used type of factor analysis, principle components analysis, contributes to the amount of error in statistical analysis. In the study, which concerns email use, factor analyses were performed using several different factor analysis ..."
Abstract
 Add to MetaCart
Computer Information Systems This study demonstrates that a commonly used type of factor analysis, principle components analysis, contributes to the amount of error in statistical analysis. In the study, which concerns email use, factor analyses were performed using several different factor analysis methods. The results show that using factors derived via principle components analysis as dependent variables substantially increased the amount of error in regression analyses, and in several cases reduced the amount of explained variance.
Communicated by Steven J. Nowlan Combining Exploratory Projection Pursuit and Projection Pursuit Regression with Application to Neural Networks
"... We present a novel classification and regression method that combines exploratory projection pursuit (unsupervised training) with projection pursuit regression (supervised training), to yield a new family of costlcomplexity penalty terms. Some improved generalization properties are demonstrated on r ..."
Abstract
 Add to MetaCart
We present a novel classification and regression method that combines exploratory projection pursuit (unsupervised training) with projection pursuit regression (supervised training), to yield a new family of costlcomplexity penalty terms. Some improved generalization properties are demonstrated on realworld problems. 1
Communicated by Dana Ballad ThreeDimensional Object Recognition Using an Unsupervised BCM Network The Usefulness of Distinguishing Features
"... We propose an object recognition scheme based on a method for feature extraction from gray level images that corresponds to recent statistical theory, called pmjection pursuit, and is derived from a biologically motivated feature extracting neuron. To evaluate the performance of this method we use a ..."
Abstract
 Add to MetaCart
We propose an object recognition scheme based on a method for feature extraction from gray level images that corresponds to recent statistical theory, called pmjection pursuit, and is derived from a biologically motivated feature extracting neuron. To evaluate the performance of this method we use a set of very detailed psychophysical threedimensional object recognition experiments (Biilthoff and Edelman 1992). 1
Individualism and Collectivism: CrossCultural Perspectives on SelfIngroup Relationships
"... The individualism and collectivism constructs are theoretically analyzed and linked to certain hypothesized consequences (social behaviors, health indices). Study 1 explores the meaning of these constructs within culture (in the United States), identifying the individualdifferences variable, idioce ..."
Abstract
 Add to MetaCart
The individualism and collectivism constructs are theoretically analyzed and linked to certain hypothesized consequences (social behaviors, health indices). Study 1 explores the meaning of these constructs within culture (in the United States), identifying the individualdifferences variable, idiocentrism versus allocentrism, that corresponds to the constructs. Factor analyses of responses to items related to the constructs suggest that UrS. individualism is reflected in (a) SelfReliance With Competition, (b) Low Concern for Ingroups, and (c) Distance from Ingroups. A higher order factor analysis suggests that Subordination oflngroup Goals to Personal Goals may be the most important aspect of U.S. individualism. Study 2 probes the limits of the constructs with data from two collectivist samples (Japan and Puerto Rico) and one individualist sample (Illinois) of students. It is shown that responses depend on who the other is (i.e., which ingroup), the context, and the kind of social behavior (e.g., feel similar to other, attentive to the views of others). Study 3 replicates previous work in Puerto Rico indicating that allocentric persons perceive that they receive more and a better quality of social support than do idiocentric persons, while the latter report being more lonely than the former. Several themes, such as selfreliance, achievement, and competition, have different meanings in the two kinds of societies, and detailed examinations of the factor patterns show how such themes