Random-Coupled Neural Network
Open Access
- 31 October 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (21) , 4297
Abstract
Improving the efficiency of current neural networks and modeling them on biological neural systems have become prominent research directions in recent years. The pulse-coupled neural network (PCNN) is widely used to mimic the computational characteristics of the human brain in computer vision and neural network fields. However, PCNN faces limitations such as limited neural connections, high computational costs, and a lack of stochastic properties. This study proposes a random-coupled neural network (RCNN) to address these limitations. RCNN employs a stochastic inactivation process, selectively inactivating neural connections using a random inactivation weight matrix. This method reduces the computational burden and allows for extensive neural connections. RCNN encodes constant stimuli as periodic spike trains and periodic stimuli as chaotic spike trains, reflecting the information encoding characteristics of biological neural systems. Our experiments applied RCNN to image segmentation and fusion tasks, demonstrating its robustness, efficiency, and high noise resistance. Results indicate that RCNN surpasses traditional methods in performance across these applications.Keywords
All Related Versions
Funding Information
- Wenzhou Major Science and Technology Innovation Project (ZG2023011, 12205078)
- National Natural Science Foundation of China (ZG2023011, 12205078)
This publication has 73 references indexed in Scilit:
- Anti-noise performance of the pulse coupled neural network applied in discrimination of neutron and gamma-rayNuclear Science and Techniques, 2022
- Automated Diagnosis system for detection of the pathological brain using Fast version of Simplified Pulse-Coupled Neural Network and Twin Support Vector MachineMultimedia Tools and Applications, 2021
- An Overview of Image Segmentation Based on Pulse-Coupled Neural NetworkArchives of Computational Methods in Engineering, 2019
- Brain CT and MRI medical image fusion using convolutional neural networks and a dual-channel spiking cortical modelMedical & Biological Engineering & Computing, 2018
- An SPCNN-GVF-based approach for the automatic segmentation of left ventricle in cardiac cine MR imagesInternational Journal of Computer Assisted Radiology and Surgery, 2016
- Feature-Motivated Simplified Adaptive PCNN-Based Medical Image Fusion Algorithm in NSST DomainJournal of Digital Imaging, 2015
- Simplified parameters model of PCNN and its application to image segmentationPattern Analysis and Applications, 2015
- Multimodality medical image fusion based on new features in NSST domainBiomedical Engineering Letters, 2014
- Towards automatic power line detection for a UAV surveillance system using pulse coupled neural filter and an improved Hough transformMachine Vision and Applications, 2009
- A Simplified pulse-coupled neural network for adaptive segmentation of fabric defectsMachine Vision and Applications, 2007