Comparison of ReLU and linear saturated activation functions in neural network for universal approximation
Konferenční objektStatus neznámýpeer-reviewedpostprintSoubory
Datum publikování
2019
Autoři
Vedoucí práce
Oponent
Název časopisu
Název svazku
Vydavatel
IEEE (Institute of Electrical and Electronics Engineers)
Abstrakt
Activation functions used in hidden layers directly affect the possibilities for describing nonlinear systems using a feedforward neural network. Furthermore, linear based activation functions are less computationally demanding than their nonlinear alternatives. In addition, feedforward neural networks with linear based activation functions can be advantageously used for control of nonlinear systems, as shown in previous authors' publications. This paper aims to compare two types of linear based functions - symmetric linear saturated function and the rectifier linear unit (ReLU) function as activation functions of the feedforward neural network used for a nonlinear system approximation. Topologies with one hidden layer and the combination of defined quantities of hidden layer neurons in the feedforward neural network are used. Strict criteria are applied for the conditions of the experiments; specifically, the Levenberg-Marquardt algorithm is applied as a training algorithm and the Nguyen-Widrow algorithm is used for the weights and biases initialization. Three benchmark systems are then selected as nonlinear plants for approximation, which should serve as a repeatable source of data for testing. The training data are acquired by the computation of the output as a reaction to a specified colored input signal. The comparison is based on the convergence speed of the training for a fixed value of the error function, and also on the performance over a constant number of epochs. At the end of the experiments, only small differences between the performance of both applied activation functions are observed. Although the symmetric linear saturated activation function provides the lesser median of the final error function value across the all tested numbers of neurons in topologies, the ReLU function seems to be also capable of use as the activation function for nonlinear system modeling.
Rozsah stran
p. 146-151
ISSN
Trvalý odkaz na tento záznam
Projekt
SGS_2019_021/Výzkum pokročilých metod modelování, simulace, řízení, databázových systémů a webových aplikací
Zdrojový dokument
Proceedings of the 2019 22nd International Conference on Process Control, PC 2019
Vydavatelská verze
Přístup k e-verzi
open access
Název akce
22nd International Conference on Process Control, PC 2019 (11.06.2019 - 14.06.2019, Štrbské Pleso)
ISBN
978-1-72813-758-2
Studijní obor
Studijní program
Signatura tištěné verze
Umístění tištěné verze
Přístup k tištěné verzi
Klíčová slova
Feedforward neural network, linear saturated activation function, rectified linear activation function, nonlinear system identification, Dopředná neuronová síť, lineární saturovaná aktivační funkce, ReLU, identifikace nelineárních systémů