Auto Deep Spiking Neural Network Design Based on an Evolutionary Membrane Algorithm

In scientific research and engineering practice, the design of deep spiking neural network (DSNN) architectures remains a complex task that heavily relies on the expertise and experience of professionals. These architectures often require repeated adjustments and modifications based on factors such...

Full description

Saved in:
Bibliographic Details
Published in:Biomimetics (Basel, Switzerland) Vol. 10; no. 8; p. 514
Main Authors: Liu, Chuang, Wang, Haojie
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 06.08.2025
MDPI
Subjects:
Algorithms
Analysis
Artificial intelligence
automatic network design
Back propagation
Computational linguistics
Datasets
Deep learning
deep spiking neural network
Design
Energy efficiency
evolutionary membrane algorithm
Firing pattern
Language processing
Natural language interfaces
Natural language processing
neural architecture search
Neural networks
Neurons
Optimization techniques
spiking neural network
Unmanned aerial vehicles
deep learning
deep spiking neural network
image classification
automatic network design
spiking neural network
neural architecture search
evolutionary membrane algorithm
ISSN:2313-7673, 2313-7673
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In scientific research and engineering practice, the design of deep spiking neural network (DSNN) architectures remains a complex task that heavily relies on the expertise and experience of professionals. These architectures often require repeated adjustments and modifications based on factors such as the DSNN’s performance, resulting in significant consumption of human and hardware resources. To address these challenges, this paper proposes an innovative evolutionary membrane algorithm for optimizing DSNN architectures. This algorithm automates the construction and design of promising network models, thereby reducing reliance on manual tuning. More specifically, the architecture of DSNN is transformed into the search space of the proposed evolutionary membrane algorithm. The proposed algorithm thoroughly explores the impact of hyperparameters, such as the candidate operation blocks of DSNN, to identify optimal configurations. Additionally, an early stopping strategy is adopted in the performance evaluation phase to mitigate the time loss caused by objective evaluations, further enhancing efficiency. The optimal models identified by the proposed algorithm were evaluated on the CIFAR-10 and CIFAR-100 datasets. The experimental results demonstrate the effectiveness of the proposed algorithm, showing significant improvements in accuracy compared to the existing state-of-the-art methods. This work highlights the potential of evolutionary membrane algorithms to streamline the design and optimization of DSNN architectures, offering a novel and efficient approach to address the challenges in the applications of automated parameter optimization for DSNN.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2313-7673
2313-7673
DOI:10.3390/biomimetics10080514