Fisher's linear discriminant
E212221
dimensionality reduction method
feature extraction method
linear classifier
statistical technique
supervised learning method
Fisher's linear discriminant is a classic statistical technique for dimensionality reduction and classification that projects data onto a line to maximize separation between classes.
All labels observed (3)
| Label | Occurrences |
|---|---|
| Fisher's discriminant | 1 |
| Fisher's linear discriminant canonical | 1 |
| Fisher's linear discriminant analysis | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T1908300 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fisher's linear discriminant Context triple: [Ronald A. Fisher, knownFor, Fisher's linear discriminant]
-
A.
PCA
The PCA is an intergovernmental organization based in The Hague that facilitates arbitration and other forms of dispute resolution between states, state entities, intergovernmental organizations, and private parties.
-
B.
PCA
PCA (Principal Component Analysis) in scikit-learn is a dimensionality reduction technique that transforms high-dimensional data into a smaller set of uncorrelated components capturing the most variance.
-
C.
PCA
PCA is a conservative evangelical Presbyterian denomination in the United States known for its adherence to Reformed theology and Presbyterian church governance.
-
D.
Hotelling’s T-squared distribution
Hotelling’s T-squared distribution is a multivariate generalization of Student’s t-distribution used primarily for hypothesis testing and constructing confidence regions for mean vectors in multivariate statistics.
-
E.
LogisticRegression
LogisticRegression is a scikit-learn machine learning estimator that models the probability of class membership using a linear decision boundary with logistic (sigmoid) or related link functions.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Fisher's linear discriminant Target entity description: Fisher's linear discriminant is a classic statistical technique for dimensionality reduction and classification that projects data onto a line to maximize separation between classes.
-
A.
PCA
PCA (Principal Component Analysis) in scikit-learn is a dimensionality reduction technique that transforms high-dimensional data into a smaller set of uncorrelated components capturing the most variance.
-
B.
PCA
The PCA is an intergovernmental organization based in The Hague that facilitates arbitration and other forms of dispute resolution between states, state entities, intergovernmental organizations, and private parties.
-
C.
PCA
PCA is a conservative evangelical Presbyterian denomination in the United States known for its adherence to Reformed theology and Presbyterian church governance.
-
D.
Hotelling’s T-squared distribution
Hotelling’s T-squared distribution is a multivariate generalization of Student’s t-distribution used primarily for hypothesis testing and constructing confidence regions for mean vectors in multivariate statistics.
-
E.
LogisticRegression
LogisticRegression is a scikit-learn machine learning estimator that models the probability of class membership using a linear decision boundary with logistic (sigmoid) or related link functions.
- F. None of above. chosen
Statements (50)
| Predicate | Object |
|---|---|
| instanceOf |
dimensionality reduction method
ⓘ
feature extraction method ⓘ linear classifier ⓘ statistical technique ⓘ supervised learning method ⓘ |
| alsoKnownAs |
Fisher's linear discriminant
ⓘ
surface form:
Fisher's discriminant
Fisher's linear discriminant ⓘ
surface form:
Fisher's linear discriminant analysis
|
| assumes |
Gaussian class-conditional distributions for optimality
ⓘ
class labels are known during training ⓘ classes are linearly separable in projected space ⓘ equal covariance matrices across classes for classical derivation ⓘ |
| basedOn |
between-class covariance
ⓘ
class means ⓘ within-class covariance ⓘ |
| category | classification algorithm ⓘ |
| comparedTo |
logistic regression
ⓘ
principal component analysis ⓘ support vector machines ⓘ |
| criterion | ratio of between-class scatter to within-class scatter ⓘ |
| differsFrom | principal component analysis by using class labels ⓘ |
| generalization | multi-class linear discriminant analysis ⓘ |
| goal |
maximize between-class variance
ⓘ
maximize separation between classes ⓘ minimize within-class variance ⓘ |
| limitation |
performance degrades with highly overlapping classes
ⓘ
sensitive to small sample size relative to dimensionality ⓘ |
| mapsFrom | high-dimensional feature space ⓘ |
| mapsTo | one-dimensional subspace ⓘ |
| mathematicalForm | generalized eigenvalue problem ⓘ |
| namedAfter | Ronald A. Fisher ⓘ |
| operatesOn | labeled data ⓘ |
| optimizationObjective | Rayleigh quotient of scatter matrices ⓘ |
| output |
discriminant direction vector
ⓘ
scalar discriminant scores for samples ⓘ |
| projectionType | linear projection ⓘ |
| property | invariant to non-singular linear scaling of features ⓘ |
| relatedTo | linear discriminant analysis ⓘ |
| requires | estimation of scatter matrices ⓘ |
| typicalUseCase | two-class classification ⓘ |
| usedFor |
classification
ⓘ
dimensionality reduction ⓘ pattern recognition ⓘ supervised feature projection ⓘ |
| usedIn |
biometrics
ⓘ
face recognition ⓘ machine learning ⓘ medical diagnosis ⓘ pattern recognition ⓘ signal processing ⓘ statistics ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Fisher's linear discriminant Description of subject: Fisher's linear discriminant is a classic statistical technique for dimensionality reduction and classification that projects data onto a line to maximize separation between classes.
Referenced by (3)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
Fisher's discriminant
this entity surface form:
Fisher's linear discriminant analysis