Dragonfly visual evolutionary neural network: A novel bionic optimizer with related LSGO and engineering design optimization
Summary: Biological visual systems intrinsically include multiple kinds of motion-sensitive neurons. Some of them have been successfully used to construct neural computational models for problem-specific engineering applications such as motion detection, object tracking, etc. Nevertheless, it remain...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S258900422400261X |
| _version_ | 1797306930000035840 |
|---|---|
| author | Heng Wang Zhuhong Zhang |
| author_facet | Heng Wang Zhuhong Zhang |
| author_sort | Heng Wang |
| collection | DOAJ |
| description | Summary: Biological visual systems intrinsically include multiple kinds of motion-sensitive neurons. Some of them have been successfully used to construct neural computational models for problem-specific engineering applications such as motion detection, object tracking, etc. Nevertheless, it remains unclear how these neurons’ response mechanisms can be contributed to the topic of optimization. Hereby, the dragonfly’s visual response mechanism is integrated with the inspiration of swarm evolution to develop a dragonfly visual evolutionary neural network for large-scale global optimization (LSGO) problems. Therein, a grayscale image input-based dragonfly visual neural network online outputs multiple global learning rates, and later, such learning rates guide a population evolution-like state update strategy to seek the global optimum. The comparative experiments show that the neural network is a competitive optimizer capable of effectively solving LSGO benchmark suites with 2000 dimensions per example and the design of an operational amplifier. |
| first_indexed | 2024-03-08T00:48:57Z |
| format | Article |
| id | doaj.art-5b1c706b11ca4af2a3c06ea74b55b7c6 |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-03-08T00:48:57Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-5b1c706b11ca4af2a3c06ea74b55b7c62024-02-15T05:25:01ZengElsevieriScience2589-00422024-03-01273109040Dragonfly visual evolutionary neural network: A novel bionic optimizer with related LSGO and engineering design optimizationHeng Wang0Zhuhong Zhang1College of Big Data and Information Engineering, Guizhou University, Guiyang, Guizhou 550025, P.R. China; Tongren Polytechnic College, Tongren, Guizhou 554300, P.R. ChinaCollege of Big Data and Information Engineering, Guizhou University, Guiyang, Guizhou 550025, P.R. China; Guizhou Provincial Characteristic Key Laboratory of System Optimization and Scientific Computing, Guiyang, Guizhou 550025, P.R. China; Corresponding authorSummary: Biological visual systems intrinsically include multiple kinds of motion-sensitive neurons. Some of them have been successfully used to construct neural computational models for problem-specific engineering applications such as motion detection, object tracking, etc. Nevertheless, it remains unclear how these neurons’ response mechanisms can be contributed to the topic of optimization. Hereby, the dragonfly’s visual response mechanism is integrated with the inspiration of swarm evolution to develop a dragonfly visual evolutionary neural network for large-scale global optimization (LSGO) problems. Therein, a grayscale image input-based dragonfly visual neural network online outputs multiple global learning rates, and later, such learning rates guide a population evolution-like state update strategy to seek the global optimum. The comparative experiments show that the neural network is a competitive optimizer capable of effectively solving LSGO benchmark suites with 2000 dimensions per example and the design of an operational amplifier.http://www.sciencedirect.com/science/article/pii/S258900422400261XSensory neuroscienceComputer science |
| spellingShingle | Heng Wang Zhuhong Zhang Dragonfly visual evolutionary neural network: A novel bionic optimizer with related LSGO and engineering design optimization iScience Sensory neuroscience Computer science |
| title | Dragonfly visual evolutionary neural network: A novel bionic optimizer with related LSGO and engineering design optimization |
| title_full | Dragonfly visual evolutionary neural network: A novel bionic optimizer with related LSGO and engineering design optimization |
| title_fullStr | Dragonfly visual evolutionary neural network: A novel bionic optimizer with related LSGO and engineering design optimization |
| title_full_unstemmed | Dragonfly visual evolutionary neural network: A novel bionic optimizer with related LSGO and engineering design optimization |
| title_short | Dragonfly visual evolutionary neural network: A novel bionic optimizer with related LSGO and engineering design optimization |
| title_sort | dragonfly visual evolutionary neural network a novel bionic optimizer with related lsgo and engineering design optimization |
| topic | Sensory neuroscience Computer science |
| url | http://www.sciencedirect.com/science/article/pii/S258900422400261X |
| work_keys_str_mv | AT hengwang dragonflyvisualevolutionaryneuralnetworkanovelbionicoptimizerwithrelatedlsgoandengineeringdesignoptimization AT zhuhongzhang dragonflyvisualevolutionaryneuralnetworkanovelbionicoptimizerwithrelatedlsgoandengineeringdesignoptimization |