Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: nature inspired algorithm

Sortuj według:

Ogranicz wyniki do:

NiaNet: A framework for constructing Autoencoder architectures using nature-inspired algorithms

100%

Pavlič S. , Fister Jr. I. , Karakatič S.

Annals of Computer Science and Information Systems

2022

tom Vol. 30

109--116

Autoencoder, an hourly glass-shaped deep neural network capable of learning data representation in a lower dimension, has performed well in various applications. However, developing a high-quality AE system for a specific task heavily relies on human expertise, limiting its widespread application. On the other hand, there has been a gradual increase in automated machine learning for developing deep learning systems without human intervention. However, there is a shortage of automatically designing particular deep neural networks such as AE. This study presents the NiaNet method and corresponding software framework for designing AE topology and hyper-parameter settings. Our findings show that it is possible to discover the optimal AE architecture for a specific dataset without the requirement for human expert assistance. The future potential of the proposed method is also discussed in this paper.

Application of the path-repairing technique and virus optimization algorithm for the dimensional synthesis of four-bar mechanisms

100%

Grabski J. K. , Sopa M. , Mrozek A.

Archives of Civil and Mechanical Engineering

2023

tom Vol. 23, no. 2

art. no. e134, 2023

This paper considers the synthesis of the four-bar mechanism. It is treated here as an optimization problem, in which an objective function is defined. To solve this problem, a metaheuristic called the virus optimization algorithm is employed. Furthermore, a new path-repairing technique recently published by Sleesongsom and Bureerat is applied instead of the very common technique related to the application of a penalty function. This makes the search by means of the metaheuristic more efficient. Furthermore, the obtained results are very accurate.