The Fisher Information as a Neural Guiding Principle for Independent Component Analysis
نویسندگان
چکیده
منابع مشابه
The Fisher Information as a Neural Guiding Principle for Independent Component Analysis
The Fisher information constitutes a natural measure for the sensitivity of a probability distribution with respect to a set of parameters. An implementation of the stationarity principle for synaptic learning in terms of the Fisher information results in a Hebbian self-limiting learning rule for synaptic plasticity. In the present work, we study the dependence of the solutions to this rule in ...
متن کاملNeural independent component analysis by "maximum-mismatch" learning principle
The aim of the present paper is to apply Sudjanto-Hassoun theory of Hebbian learning to neural independent component analysis. The basic learning theory is first recalled and expanded in order to make it suitable for a network of non-linear complex-weighted neurons; then its interpretation and application is shown in the context of blind separation of complex-valued sources. Numerical results a...
متن کاملFisher information matrix: A tool for dimension reduction, projection pursuit, independent component analysis, and more
Hui & Lindsay (2010) proposed a new dimension reduction method for multivariate data. It was based on the so-called white noise matrices derived from the Fisher information matrix. Their theory and empirical studies demonstrated that this method can detect interesting features from high-dimensional data even with a moderate sample size. The theoretical emphasis in that paper was the detection o...
متن کاملThe Church-Turing thesis as a guiding principle for physics
Two aspects of the physical side of the Church-Turing thesis are discussed. The first issue is a variant of the Eleatic argument against motion, dealing with Zeno squeezed time cycles of computers. The second argument reviews the issue of one-to-one computation, that is, the bijective (unique and reversible) evolution of computations and its relation to the measurement process.
متن کاملMinimal Nonlinear Distortion Principle for Nonlinear Independent Component Analysis
It is well known that solutions to the nonlinear independent component analysis (ICA) problem are highly non-unique. In this paper we propose the “minimal nonlinear distortion” (MND) principle for tackling the ill-posedness of nonlinear ICA problems. MND prefers the nonlinear ICA solution with the estimated mixing procedure as close as possible to linear, among all possible solutions. It also h...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Entropy
سال: 2015
ISSN: 1099-4300
DOI: 10.3390/e17063838