.png){kind=icon}
Return
Training feedforward neural networks using multi-verse optimizer for binary classification problems
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-016-0767-1.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper employs the recently proposed nature-inspired algorithm called Multi-Verse Optimizer (MVO) for training the Multi-layer Perceptron (MLP) neural network. The new training approach is benchmarked and evaluated using nine different bio-medical datasets selected from the UCI machine learning repository. The results are compared to five classical and recent evolutionary metaheuristic algorithms: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution (DE), FireFly (FF) Algorithm and Cuckoo Search (CS). In addition, the results are compared with two well-regarded conventional gradient-based training methods: the conventional Back-Propagation (BP) and the Levenberg-Marquardt (LM) algorithms. The comparative study demonstrates that MVO is very competitive and outperforms other training algorithms in the majority of datasets in terms of improved local optima avoidance and convergence speed.
Keywords:
Multi-verse optimizer
MVO
Multilayer perceptron
MLP
Training neural network
Evolutionary algorithm
Journal
IF:
3.5
Papers:
7.6K
Citations:
1.7W
Organization
Cited Papers
ShareSaveShareSaveSurface Enrichment in Equimolar Mixtures of Non‐Functionalized and Functionalized Imidazolium‐Based Ionic Liquids.png)
ChemPhysChem
OAAI
ChemPhysChemIF0
OAAIShareSaveShareSaveA series of transition metal coordination polymers based on a rigid bi-functional carboxylate–triazolate tectonCrystEngComm
CrystEngCommIF0
PREAI
ShareSave
ShareSave
View more