The generalized proportional-integral-derivative (PID) gradient descent back propagation algorithm

Vitthal, Ramana; Sunthar, P.; Rao, Ch. Durgaprasada

doi:10.1016/0893-6080(94)00100-z

Cited by 15 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of PID laws in various nonlinear optimization problems have revealed a different and interesting application field besides their conventional use for the minimization of error signals in control systems. For example, it has been presented that the problems related to reaching the global minimum can be solved by providing better convergence speed by using PID actions in the conventional gradient descent algorithm [2]. In another study, a three term backpropagation algorithm was developed by adding a proportional action to the standard backpropagation algorithm, and it was shown to be successful in terms of convergence rate and local minimums for artificial neural networks training [3].…”

Section: Introductionmentioning

confidence: 99%

PID tabanlı optimize edici döngüsü için bir uygulama: Malatya kayısısının yıllık üretim regresyon modellerinin tahmini

Deniz

2022

DÜMF MD

View full text Add to dashboard Cite

In this study, a data analysis application for the PID-based optimizer loop, which was previously proposed in a former study, is carried out. In this application, quadratic and cubic polynomial regression models were obtained for the estimation of annual apricot production by using the yearly total apricot production data of Malatya between 1991 and 2020. In addition, an average of these regression model estimations was calculated to increase estimation reliability. Annual apricot production amount was estimated by using the regression models obtained with the PID-based optimizer system between 2021-2025. The results were compared with the results obtained with the Matlab curve fitting toolbox.

show abstract

Section: Introductionmentioning

confidence: 99%

PID tabanlı optimize edici döngüsü için bir uygulama: Malatya kayısısının yıllık üretim regresyon modellerinin tahmini

Deniz

2022

DÜMF MD

View full text Add to dashboard Cite

show abstract

“…There are a number of ways to decrease the training time. Several improvements have been made to the rule used to adjust the weights to increase the rate of descent down the error surface or to decrease a network's likelihood of being trapped in a local minima [5]. For example, the conjugate gradient method can in some cases decrease the number of iterations by an order of magnitude [6].…”

Section: Introductionmentioning

confidence: 99%

High-performance simulation of neural networks

Rademacher

Lumpp²

1997

1997 IEEE Aerospace Conference

View full text Add to dashboard Cite

Artificial neural networks have been used for a wide range of problems in a variety of areas. The back-propagation algorithm is frequently used to train the network, but is time consuming when implemented on generalpurpose computers. This paper examines methods of simulating back-propagation neural networks on parallel systems to achieve high performance. The training of artificial neural networks consists of updating the weights in several nested loops. Parallel simulation methods may be classified based on which of these loops are executed in parallel. These methods are discussed and example implementations of these methods are described.

show abstract

Data mining using a genetic algorithm‐trained neural network

Sexton

Sikander

2001

Intelligent Systems in Accounting, Finance and Management

View full text Add to dashboard Cite

Neural networks have been shown to perform well for mapping unknown functions from historical data in many business areas, such as accounting, finance, and management. Although there have been many successful applications of neural networks in business, additional information about the networks is still lacking, specifically, determination of inputs that are relevant to the neural network model. It is apparent that by knowing which inputs are actually contributing to model prediction a researcher has gained additional knowledge about the problem itself. This can lead to a parsimonious neural network architecture, better generalization for out‐of‐sample prediction, and, probably the most important, a better understanding of the problem. It is shown in this paper that by using a modified genetic algorithm for neural network training, relevant inputs can be determined while simultaneously searching for a global solution. Copyright © 2001 John Wiley & Sons, Ltd.

show abstract

The generalized proportional-integral-derivative (PID) gradient descent back propagation algorithm

Cited by 15 publications

References 10 publications

PID tabanlı optimize edici döngüsü için bir uygulama: Malatya kayısısının yıllık üretim regresyon modellerinin tahmini

PID tabanlı optimize edici döngüsü için bir uygulama: Malatya kayısısının yıllık üretim regresyon modellerinin tahmini

High-performance simulation of neural networks

Data mining using a genetic algorithm‐trained neural network

Contact Info

Product

Resources

About