Single-layer perceptron artificial visual system for orientation detection
Orientation detection is an essential function of the visual system. In our previous works, we have proposed a new orientation detection mechanism based on local orientation-selective neurons. We assume that there are neurons solely responsible for orientation detection, with each neuron dedicated t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-08-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1229275/full |
| _version_ | 1797739567188541440 |
|---|---|
| author | Hiroyoshi Todo Tianqi Chen Jiazhen Ye Bin Li Yuki Todo Zheng Tang |
| author_facet | Hiroyoshi Todo Tianqi Chen Jiazhen Ye Bin Li Yuki Todo Zheng Tang |
| author_sort | Hiroyoshi Todo |
| collection | DOAJ |
| description | Orientation detection is an essential function of the visual system. In our previous works, we have proposed a new orientation detection mechanism based on local orientation-selective neurons. We assume that there are neurons solely responsible for orientation detection, with each neuron dedicated to detecting a specific local orientation. The global orientation is inferred from the local orientation information. Based on this mechanism, we propose an artificial visual system (AVS) by utilizing a single-layer of McCulloch-Pitts neurons to realize these local orientation-sensitive neurons and a layer of sum pooling to realize global orientation detection neurons. We demonstrate that such a single-layer perceptron artificial visual system (AVS) is capable of detecting global orientation by identifying the orientation with the largest number of activated orientation-selective neurons as the global orientation. To evaluate the effectiveness of this single-layer perceptron AVS, we perform computer simulations. The results show that the AVS works perfectly for global orientation detection, aligning with the majority of physiological experiments and models. Moreover, we compare the performance of the single-layer perceptron AVS with that of a traditional convolutional neural network (CNN) on orientation detection tasks. We find that the single-layer perceptron AVS outperforms CNN in various aspects, including identification accuracy, noise resistance, computational and learning cost, hardware implementation feasibility, and biological plausibility. |
| first_indexed | 2024-03-12T13:59:04Z |
| format | Article |
| id | doaj.art-ae6e67fa877c4e8f93edef1cb7e68640 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-03-12T13:59:04Z |
| publishDate | 2023-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-ae6e67fa877c4e8f93edef1cb7e686402023-08-22T08:59:26ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-08-011710.3389/fnins.2023.12292751229275Single-layer perceptron artificial visual system for orientation detectionHiroyoshi Todo0Tianqi Chen1Jiazhen Ye2Bin Li3Yuki Todo4Zheng Tang5Wicresoft Co., Ltd, Tokyo, JapanDivision of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa, JapanChengfang Financial Information Technology Service Corporation, Beijing, ChinaDivision of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa, JapanDivision of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa, JapanDepartment of Intelligence Information Systems, University of Toyama, Toyama, JapanOrientation detection is an essential function of the visual system. In our previous works, we have proposed a new orientation detection mechanism based on local orientation-selective neurons. We assume that there are neurons solely responsible for orientation detection, with each neuron dedicated to detecting a specific local orientation. The global orientation is inferred from the local orientation information. Based on this mechanism, we propose an artificial visual system (AVS) by utilizing a single-layer of McCulloch-Pitts neurons to realize these local orientation-sensitive neurons and a layer of sum pooling to realize global orientation detection neurons. We demonstrate that such a single-layer perceptron artificial visual system (AVS) is capable of detecting global orientation by identifying the orientation with the largest number of activated orientation-selective neurons as the global orientation. To evaluate the effectiveness of this single-layer perceptron AVS, we perform computer simulations. The results show that the AVS works perfectly for global orientation detection, aligning with the majority of physiological experiments and models. Moreover, we compare the performance of the single-layer perceptron AVS with that of a traditional convolutional neural network (CNN) on orientation detection tasks. We find that the single-layer perceptron AVS outperforms CNN in various aspects, including identification accuracy, noise resistance, computational and learning cost, hardware implementation feasibility, and biological plausibility.https://www.frontiersin.org/articles/10.3389/fnins.2023.1229275/fullperceptronsingle-layervisual systemorientation detectioncomputer vision |
| spellingShingle | Hiroyoshi Todo Tianqi Chen Jiazhen Ye Bin Li Yuki Todo Zheng Tang Single-layer perceptron artificial visual system for orientation detection Frontiers in Neuroscience perceptron single-layer visual system orientation detection computer vision |
| title | Single-layer perceptron artificial visual system for orientation detection |
| title_full | Single-layer perceptron artificial visual system for orientation detection |
| title_fullStr | Single-layer perceptron artificial visual system for orientation detection |
| title_full_unstemmed | Single-layer perceptron artificial visual system for orientation detection |
| title_short | Single-layer perceptron artificial visual system for orientation detection |
| title_sort | single layer perceptron artificial visual system for orientation detection |
| topic | perceptron single-layer visual system orientation detection computer vision |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1229275/full |
| work_keys_str_mv | AT hiroyoshitodo singlelayerperceptronartificialvisualsystemfororientationdetection AT tianqichen singlelayerperceptronartificialvisualsystemfororientationdetection AT jiazhenye singlelayerperceptronartificialvisualsystemfororientationdetection AT binli singlelayerperceptronartificialvisualsystemfororientationdetection AT yukitodo singlelayerperceptronartificialvisualsystemfororientationdetection AT zhengtang singlelayerperceptronartificialvisualsystemfororientationdetection |