Background on dynamic neural networks

Poznyak, Tatyana; Oria, Isaac Chairez; Poznyak, Alexander S.

doi:10.1016/b978-0-12-812847-3.00012-3

Cited by 19 publications

(21 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-S-elements, the purpose of which is to model the receptor layer or the input layer of an artificial neuron; -A-elements intended for association modeling (hidden layer); -R-elements are used to model the response of an artificial neural network (the output layer of the neural network); -W is the interaction matrix, i.e., the weights of the synapses connecting the layers of the artificial neural network; -B is the displacement neuron [11].…”

Section: Resultsmentioning

confidence: 99%

Model of an Artificial Neural Network for Solving the Problem of Controlling a Genetic Algorithm Using the Mathematical Apparatus of the Theory of Petri Nets

Петросов

Lomazov

Petrosova³

2021

Applied Sciences

View full text Add to dashboard Cite

The aim of the study was to increase the speed, quantity and quality of solutions in intelligent systems aimed at solving the problem of structural–parametric synthesis of models of large discrete systems with a given behavior. As a hypothesis, it was assumed that the adapted model of an artificial neural network is able to control changes in the parameters of the functioning of the operators of the genetic algorithm directly in the process of solving the problem of intelligent structural–parametric synthesis of models of large discrete systems. To solve the problem of managing the process of intelligent search for solutions based on a genetic algorithm, an artificial neural network, which is used as an add-in, must dynamically change the “destructive” ability of operators based on data about the current and/or historical state of the population. In the article, the theory of Petri nets is used as a single mathematical device capable of modeling the work of evolutionary procedures. This mathematical tool is able to simulate the operation of a genetic algorithm adapted to solving the problem of structural–parametric synthesis of models of large discrete systems with a given behavior; simulate the operation and training of an artificial neural network; combine the genetic algorithm with a control add-in based on an artificial neural network to prevent attenuation and premature convergence; simulate the process of recognizing the state of the population; and simulate the operation of the models obtained as a result of the synthesis. As an example of the functioning of the proposed approach, the article presents the results of a computational experiment, which considers the problem of structural–parametric synthesis of computer technology based on the developed models of the element base-RS, D and T triggers that are capable of processing a given input vector into the required (reference) output. In the software implementation of the proposed approach, calculations on the CPU and CPU+GPGPU technologies were used.

show abstract

Section: Resultsmentioning

confidence: 99%

Model of an Artificial Neural Network for Solving the Problem of Controlling a Genetic Algorithm Using the Mathematical Apparatus of the Theory of Petri Nets

Петросов

Lomazov

Petrosova³

2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…When the original dynamics in ( 3 ) is completely or partially unknown, we suggest applying the DNN approach [ 11 ] which showed nice results being applied to various problems in bio-engineering and the environment science [ 12 , 13 ].…”

Section: Prediction Algorithm For Models With Incomplete Information:...mentioning

confidence: 99%

Differential Neural Networks Prediction Using Slow and Fast Hybrid Learning: Application to Prognosis of Infectionsand Deaths of COVID-19 Dynamics

Poznyak

Chairez

Anyutin

2023

Neural Process Lett

View full text Add to dashboard Cite

This essay discusses a potential method for predicting the behavior of various physical processes and uses the COVID-19 outbreak to demonstrate its applicability. This study assumes that the current data set reflects the output of a dynamic system that is governed by a nonlinear ordinary differential equation. This dynamic system may be described by a Differential Neural Network (DNN) with time-varying weights matrix parameters. A new hybrid learning scheme based on the decomposition of the signal to be predicted. The decomposition considers the slow and fast components of the signal which is more natural to signals such as the ones corresponding to the number of infected and deceased patients who suffered of COVID 2019 sickness. The paper results demonstrate the recommended method offers competitive performance (70 days of COVID prediction) in comparison to similar studies.

show abstract

“…While shallow neural networks with a single hidden layer are faster to train and can run on machines with smaller resources, DNNs are able to model mapping with higher complexity and can be as effective as shallow neural networks when their parameters are optimized (81)(82)(83). In contrast to FFNNs, recurrent neural networks (RNN) have feedback loops, which allow signals to travel backward to previous parts of the network (84,85). As a result, it allows information to persist and has the built-in capability of modelling sequential data, therefore, it is applied in model predictive control (MPC) (86,87).…”

Section: Application Of Artificial Neural Network and Multivariate Data Analysis As Complementary Tools In Pharmaceutical Developmentmentioning

confidence: 99%

Quality-by-design in pharmaceutical development: From current perspectives to practical applications

et al. 2021

View full text Add to dashboard Cite

Current pharmaceutical research directions tend to follow a systematic approach in the field of applied research and development. The concept of quality-by-design (QbD) has been the focus of the current progress of pharmaceutical sciences. It is based on, but not limited, to risk assessment, design of experiments and other computational methods and process analytical technology. These tools offer a well-organized methodology, both to identify and analyse the hazards that should be handled as critical, and are therefore applicable in the control strategy. Once implemented, the QbD approach will augment the comprehension of experts concerning the developed analytical technique or manufacturing process. The main activities are oriented towards the identification of the quality target product profiles, along with the critical quality attributes, the risk management of these and their analysis through in silico aided methods. This review aims to offer an overview of the current standpoints and general applications of QbD methods in pharmaceutical development.

show abstract

Background on dynamic neural networks

Cited by 19 publications

References 3 publications

Model of an Artificial Neural Network for Solving the Problem of Controlling a Genetic Algorithm Using the Mathematical Apparatus of the Theory of Petri Nets

Model of an Artificial Neural Network for Solving the Problem of Controlling a Genetic Algorithm Using the Mathematical Apparatus of the Theory of Petri Nets

Differential Neural Networks Prediction Using Slow and Fast Hybrid Learning: Application to Prognosis of Infectionsand Deaths of COVID-19 Dynamics

Quality-by-design in pharmaceutical development: From current perspectives to practical applications

Contact Info

Product

Resources

About