ML Anthology

Closed-Form Expressions of Some Stochastic Adapting Equations for Nonlinear Adaptive Activation Function Neurons

Simone G. O. Fiori
NeCo 2003 pp. 2909-2929
doi:10.1162/089976603322518795 /neco/2003/fiori2003neco-closedform/

Abstract

In recent work, we introduced nonlinear adaptive activation function (FAN) artificial neuron models, which learn their activation functions in an unsupervised way by information-theoretic adapting rules. We also applied networks of these neurons to some blind signal processing problems, such as independent component analysis and blind deconvolution. The aim of this letter is to study some fundamental aspects of FAN units' learning by investigating the properties of the associated learning differential equation systems.

NeCo Semantic Scholar

Cite

Text

Fiori. "Closed-Form Expressions of Some Stochastic Adapting Equations for Nonlinear Adaptive Activation Function Neurons." Neural Computation, 2003. doi:10.1162/089976603322518795

Markdown

[Fiori. "Closed-Form Expressions of Some Stochastic Adapting Equations for Nonlinear Adaptive Activation Function Neurons." Neural Computation, 2003.](https://mlanthology.org/neco/2003/fiori2003neco-closedform/) doi:10.1162/089976603322518795

BibTeX

@article{fiori2003neco-closedform,
  title     = {{Closed-Form Expressions of Some Stochastic Adapting Equations for Nonlinear Adaptive Activation Function Neurons}},
  author    = {Fiori, Simone G. O.},
  journal   = {Neural Computation},
  year      = {2003},
  pages     = {2909-2929},
  doi       = {10.1162/089976603322518795},
  volume    = {15},
  url       = {https://mlanthology.org/neco/2003/fiori2003neco-closedform/}
}