Fisher Score
Jump to navigation
Jump to search
A Fisher Score is a Statistical Significance Test Score.
- …
- Counter-Example(s):
- See: Fisher Discriminant Analysis, Fisher Kernel, Statistical Significance Test, t-Test, P Value, Log-Likelihood.
References
2014
- (Wikipedia, 2014) ⇒ http://en.wikipedia.org/wiki/Fisher_kernel#Fisher_score Retrieved:2014-9-29.
- The Fisher kernel makes use of the Fisher score, defined as : [math]\displaystyle{ U_X = \nabla_{\theta} \log P(X|\theta) }[/math] with θ being a set (vector) of parameters. The function taking θ to log P(X|θ) is the log-likelihood of the probabilistic model.