NEURON MODEL SIGMOID ACTIVATION FUNCTION BASED ON MULTI-OPTIONAL FUNCTIONS ENTROPY CONDITIONAL OPTIMIZATION DOCTRINE

Abstract

It is made an attempt to discover an explainable plausible reason for a neuron activation function, of a sigmoid type function like logistic function, substantiation in terms of the multi-optional conditional optimality doctrine for the special hybrid-optional effectiveness functions uncertainty. In the studied case, the input-output mapping is stipulated by the entropy of the activation function conditional optimal distribution in regards with the induced local field of the neuron. It is proposed to evaluate the direction of uncertainty with the combined hybrid relative pseudo-entropy function. This is a new insight into the scientific substantiation of the well-known dependency derived in another way. The developed theoretical contemplations and mathematical derivations are verified with numerical simulation and plotted diagrams.

Authors and Affiliations

Andriy Goncharenko

Keywords

Related Articles

STRUCTURAL-PARAMETRIC SYNTHESIS OF THE FEEDFORWARD NEURAL NETWORKS WITH SIGMOID PIECEWISE-TYPE NEURONS

The method of structural and parametric synthesis of feedforward neural networks is considered, which includes Sigmoid Piecewise neurons, used in the process of a predictive model construction. The article describes the...

COMPUTER-AIDED DESIGN OF FIXED WING UAV PATH TRACKING SYSTEM

In this paper problem of smooth fixed-wing unmanned aerial vehicle path following is considered, when the reference path is the linear piecewise trajectory having points of discontinuity with abrupt changing of the headi...

TEST BENCH OF AXIAL GENERATORS OF WIND POWER PLANTS

This article is devoted to the construction of a test bench for quality control of an axial generator, which is a part of a low-power wind power plant. The axial generator reaches the working power at a wind speed of 3–3...

PARAMETRICAL SYNTHESIS OF ROBUST SYSTEM FOR STABILIZATION OF AIRCRAFT EQUIPMENT

The paper deals with parametrical synthesis of robust system assigned for stabilization of aircraft equipment. The mathematical model of the stabilization plant is represented. The algorithm of parametrical synthesis of...

INTEGRATED MICROMECHANICAL GYROVERTICAL

The dubiousness of instantiation of the gyroverticales which based on micromechanical accelerometers and on micromechanical gyroscopic sensors is shown. Based on the analysis of the frequency characteristics of the err...

Download PDF file
  • EP ID EP514740
  • DOI 10.18372/1990-5548.58.13518
  • Views 149
  • Downloads 0

How To Cite

Andriy Goncharenko (2018). NEURON MODEL SIGMOID ACTIVATION FUNCTION BASED ON MULTI-OPTIONAL FUNCTIONS ENTROPY CONDITIONAL OPTIMIZATION DOCTRINE. Електроніка та системи управління, 4(58), 108-114. https://europub.co.uk/articles/-A-514740