Realizations of the Artificial Neural Network for Process Modeling. Overview of Current Implementations

Abstract

This work is intended to review the most typical realizations of Artificial Neural Networks (ANNs), implemented in a Feedforward Neural Network (FNN) as well as a Recurrent Neural Network (RNN). Essential differences in ANN architecture and basic operating principles are discussed. The problems of learning processes are presented in several cuts. The advantages of prediction using ANNs have been demonstrated in several popular fields such as adaptive educology, classification of medicine and biology, industry, etc.

Validation Challenges in Data for Different Diesel Engine Performance Regimes Utilising HVO Fuel: A Study on the Application of Artificial Neural Networks for Emissions Prediction

“…The second stage pertains to the selection of the artificial neural network architecture. The feedforward method (information flow from the input layer through hidden layers to the output layer) was chosen due to the cause-and-effect relationship [37]. The possibility of using an ANN containing a single-hidden layer and multi-hidden layers was discovered and estimated.…”