Design of Dynamic Modular Neural Network Based on Adaptive Particle Swarm Optimization Algorithm

To solve the problem that subnetwork output cannot be optimally integrated in a modular neural network (MNN), this paper proposes an adaptive particle swarm optimization algorithm for dynamic MNN (APSO-DMNN). First, the method identifies the distribution of samples and updates the training parameter...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE access Ročník 6; s. 10850 - 10857
Hlavní autoři: Qiao, Jun-Fei, Lu, Chao, Li, Wen-Jing
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.01.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Adaptive algorithms
adaptive particle swarm optimization algorithm
Algorithm design and analysis
Biological neural networks
dynamic output integration
Heuristic algorithms
Modular design
Modular neural network
Multi-layer neural network
Neural networks
Neurons
Optimization algorithms
Parameter identification
Particle swarm optimization
Task analysis
time varying system
ISSN:2169-3536, 2169-3536
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To solve the problem that subnetwork output cannot be optimally integrated in a modular neural network (MNN), this paper proposes an adaptive particle swarm optimization algorithm for dynamic MNN (APSO-DMNN). First, the method identifies the distribution of samples and updates the training parameters based on data potential. Second, the MNN activates the corresponding subnetworks according to the input data. Calculate the weights based on an APSO algorithm, which can dynamically optimize the contribution of the output. Then, the inertia weights in the APSO algorithm are adjusted by a nonlinear function in order to avoid being trapped into local optimal values. Finally, the proposed APSO-DMNN can be obtained based on the optimal integration and dynamic adjustment. Comparisons with other algorithms indicate that the proposed method is more effective in modeling and predicting.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2018.2803084