ONE INCREMENTAL ADAPTATION STRATEGY OF THE DECISION-MAKING FORMAL NEURON

Abstract

 The general objective of formal neuron adaptation is to give the reliable inputs more influence in determining the output than the unreliable inputs have. Adaptation is introduced into the threshold decision element by a circuit that performs two operations: estimates the error probability of each input and uses the estimate to change each voteweight. A cyclic error-counting adaptation procedure is the one in which vote-weights are changed periodically (cyclically), based on data collected during computations in a period (cycle). If appropriate incremental adjustments are made to the estimate of inputs' each error after each computation, then we deal with continuous adaptation. There are two methods for detecting errors: comparison with the output decision (closed-loop adaptation) and comparison with an externally supplied correct answer (open-loop adaptation). In this paper, the input weighted sum is compared with the desired value of this sum, which is multiplied by the correct binary answer. Our results for incremental changes of the input weights of the adaptive formal neuron are based on the Widrow-Hoff algorithm and stochastic approximation method.

Authors and Affiliations

Archil Prangishvili, Natia Namicheishvili

Keywords

Related Articles

 A Novel Framework for Composite Network Security Situation Assessment Using HRCAL Approach

 In the present era computer network is taken as the core component of various technology supported areas such as banking sector, emergency systems and communication areas. With this increase in network usage the k...

 Analysis of the Design of Helical Compression Spring to Study the Behaviour of Steel and Composites Used as Spring Materials

 Presently the automobile manufacturers are facing challenges of improvements in the quality and performance of the components together with the reduction in weight and cost of manufacturing. Efforts are directed...

 PREDICTION OF FAILURES IN BUILDINGS USING SENSORS

 The paper deals with the prediction of failure in flexural members such as beams when subjected to overloading condition due to live loads, vibrations…etc,. The sensors are installed in the member to predict the fa...

 EFFECTS OF INITIAL MOISTURE CONTENT AND HEATING RATE ON WHEAT (OAKES) DRYING KINETIC PARAMETERS

 The goal of this study was to determine the effects of initial moisture content and heating rate on the drying kinetic parameters of wheat under non-isothermal conditions. Wheat (OAKES) samples at initial moisture...

 3-Bit R-2R Digital to Analog Converter Using Binary and Thermometer Code

 In this paper analysis of 3-bit R-2r ladder DAC designed with the specification of INL &DNL .The simulation & analysis is done using the binary and thermometer code. In this design DAC the Maximum INL &amp...

Download PDF file
  • EP ID EP94846
  • DOI -
  • Views 73
  • Downloads 0

How To Cite

Archil Prangishvili, Natia Namicheishvili (2015).  ONE INCREMENTAL ADAPTATION STRATEGY OF THE DECISION-MAKING FORMAL NEURON. International Journal of Engineering Sciences & Research Technology, 4(1), 333-346. https://europub.co.uk/articles/-A-94846