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...
NONLINEAR ROBUST CONTROL SYSTEM FOR STABILIZATION OF MARINE VEHICLES
Nonlinear robust control system, that improves marine vehicle’s control process under condition of a marine vehicle’s and environment’s uncertainty, is considered in the article. Nonlinear robust system allows to keep a...
EMERGENCY ACCESSION OPERATIONAL VIDEO CONTROL SYSTEM
A brief overview of the gathering information existing means about the emergencies is given. The system with the artillery launch of aerospace video surveillance equipment is considered, and the structure and functioning...
ALGORITHM OF PRUNING OF HYBRID NEURAL NETWORKS ENSEMBLE
Despite the fact that the ensemble is usually more accurate than a single network, existing ensemble techniques tend to create unreasonably large ensembles that increase the use of memory and computation costs. The ensem...
MULTIFUNCTIONAL ROBOTIC COMPLEX BASED ON A SINGLE-BOARD COMPUTER
The necessity of organization and implementation of the aircraft elements deformations continuous control for the timely detection of their critical values is shown. A brief overview of existing methods and devices for m...