NEURON MODEL SIGMOID ACTIVATION FUNCTION BASED ON MULTI-OPTIONAL FUNCTIONS ENTROPY CONDITIONAL OPTIMIZATION DOCTRINE
Journal Title: Електроніка та системи управління - Year 2018, Vol 4, Issue 58
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
THE OPTIMUM REGULATOR FOR THE NONLINEAR STABILIZATION SYSTEM OF THE INERTIAL CONTROL OBJECT
Designed the model of the nonlinear stabilization system of the ship course and showed experimental and theoretical research results of the selection an optimal regulator for the system, which excludes, at the same time...
CALCULATION OF THE GAS-DYNAMIC COMPLEX SIZES
In the paper exact and approximation analytical expressions for calculation of the gas-dynamic jets parameters for gas-dynamic complex are obtained. The sizes of gas-dynamic complex for providing of the unmanned aerial v...
COMPENSATION OF QUADRATURED ERROR IN THE AUTO-OSCILLATION MICROMECHANICAL GYROSCOPE
In this paper, attention was paid to the analysis of the micromechanical sensor unit of the inertial navigation system as the main component of an unmanned aerial vehicle, as well as to improve the technical characterist...
INTELLIGENT SYSTEM OF DIAGNOSTICS OF THYROID GLAND PATHOLOGY
It is considered a principle of thyroid pathology diagnostics intelligent system structure. It is determined basic ultrasound images features for patients with thyroid cancers. The block diagram of intellectual diagnosti...
INTELLIGENT WEATHER FORECAST SYSTEM
It is considered the creation of intelligent weather forecast system in traditional statement as the prediction of time series For the solution of this problem it is chosen a random forest algorithm. Examples of program...