THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS

By R. Fisher. 1936

Subfields: Statistics and Probability, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

In Statistical Learning Theory

Citations in the corpus

AutoML: A Survey of the State-of-the-Art (2019, background): “[49] develop a synthetic data definition language (SDDL) to create new data for Iris dataset [50].”
A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, methodology): “Linear Discriminant Analysis (LDA) [100] is a supervised statistical method to ﬁnd linear combinations of features that achieve good separation of classes.”
Prototypal Analysis and Prototypal Regression (2017, methodology): “t through the alternate minimization over the c and τ. 4.3 Applications 4.3.1 Iris Flowers We apply multiple prototypal regression to the data set for classiﬁcation of Iris into species introduced by Fisher (1936). This includes three Iris species with four features for each ﬂower: sepal length, sep”
Strongly agree or strongly disagree?: Rating features in Support Vector Machines (2016, methodology): “Third, our approach can also be extended to other linear classi ers, such as the classical Linear Discriminant Analysis (Fisher 1936) and the Logistic Regression (Hastie et al. 2001), where building the new classi er yields Nonlinear Integer Programming problems (Burer and Letchford 2012).”
On the Schoenberg Transformations in Data Analysis: Theory and Illustrations (2010, methodology): “…each object i to the group g whose centroid is the closest to i , that is to assign i to arg min g D ig : this is the linear discriminant prescription of Fisher (1936), successfully applied on the Iris Data ( n = 150, p = 4, m = 3) with a percentage of well-classiﬁed individuals as high as 97%.”
How to Explain Individual Classification Decisions (2009, neutral): “The Iris ﬂower data set (introduced in Fisher, 1936) describes 150 ﬂowers from the genus Iris by 4 features: sepal length, sepal width, petal length, and petal width, which are easily measured properties of certain leaves of the corolla of the ﬂower.”
On the interpretation of weight vectors of linear models in multivariate neuroimaging (2014, background): “…analysis As an example of how extraction ﬁ lters depend on the spatial structure of the noise, consider the case of linear discriminant analysis (LDA) classi ﬁ cation (Fisher, 1936), which is the Bayes optimal classi ﬁ cation rule for Gaussian distributed classes with equal covariance matrices.”
Examining Gender Bias in Languages with Grammatical Gender (2019, methodology): “Therefore, instead of applying PCA, we learn the grammatical gender direction ~ dg by Linear Discriminant Analysis (LDA) (Fisher, 1936), which is a standard approach for supervised dimension reduction.”
A tutorial on conformal prediction (2007, background): “1 Example: Classifying iris flowers In 1936 [11], R.”
Between-Class Learning for Image Classification (2017, background): “• Enlargement of Fisher’s criterion [8] (i.”
Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning (2023, background): “It describes an optimal geometric structure for classiﬁcation due to the minimized within-class variance and the maximized between-class variance (Martinez & Kak, 2001), which indicates that the Fisher Discriminant Ratio (Fisher, 1936; Rao, 1948) is maximized.”
Functional linear discriminant analysis for irregularly sampled curves (2001, background): “Linear discriminant analysis (LDA) is a popular procedure which dates back as far as Fisher (1936).”
Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines (2002, methodology): “In earlier work [6], we performed this classication using a Fisher linear discriminant (FLD) analysis [ 7 , 5]. Here a more exible support vector machine (SVM) classier is employed [24,25, 3]. We briey describe, in increasing complexity, three classes of SVMs.”
Distribution Calibration in Riemannian Symmetric Space (2011, methodology): “Conventional subspace learning algorithms, e.g., PCA, FLDA, and SDA, cannot work well under the cross-domain setting, because they assume that both the source- and the targetdomain samples are independent and identically distributed.”