CNN Convolutional layer optimisation based on quantum evolutionary algorithm
In this paper, a quantum convolutional neural network (CNN) architecture is proposed to find the optimal number of convolutional layers. Since quantum bits use probability to represent binary information, the quantum CNN does not represent the actual network, but the probability of existence of eac...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2021-07-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/09540091.2020.1841111 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850251231828639744 |
|---|---|
| author | Tzyy-Chyang Lu |
| author_facet | Tzyy-Chyang Lu |
| author_sort | Tzyy-Chyang Lu |
| collection | DOAJ |
| description | In this paper, a quantum convolutional neural network (CNN) architecture is proposed to find the optimal number of convolutional layers. Since quantum bits use probability to represent binary information, the quantum CNN does not represent the actual network, but the probability of existence of each convolutional layer, thus achieving the aim of training weights and optimising the number of convolutional layers at the same time. In the simulation part, CIFAR-10 (including 50k training images and 10k test images in 10 classes) is used to train VGG-19 and 20-layer, 32-layer, 44-layer and 56-layer CNN networks, and compare the difference between the optimal and non-optimal convolutional layer networks. The simulation results show that without optimisation, the accuracy of the test data drops from approximately 90% to about 80% as the number of network layers increases to 56 layers. However, the CNN with optimisation made it possible to maintain the test accuracy at more than 90%, and the number of network parameters could be reduced by nearly half or more. This shows that the proposed method can not only improve the network performance degradation caused by too many hidden convolutional layers, but also greatly reduce the use of the network’s computing resources. |
| format | Article |
| id | doaj-art-7d7dd7127c87474a9d9ad136d92ee441 |
| institution | OA Journals |
| issn | 0954-0091 1360-0494 |
| language | English |
| publishDate | 2021-07-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj-art-7d7dd7127c87474a9d9ad136d92ee4412025-08-20T01:57:55ZengTaylor & Francis GroupConnection Science0954-00911360-04942021-07-0133348249410.1080/09540091.2020.18411111841111CNN Convolutional layer optimisation based on quantum evolutionary algorithmTzyy-Chyang Lu0Providence UniversityIn this paper, a quantum convolutional neural network (CNN) architecture is proposed to find the optimal number of convolutional layers. Since quantum bits use probability to represent binary information, the quantum CNN does not represent the actual network, but the probability of existence of each convolutional layer, thus achieving the aim of training weights and optimising the number of convolutional layers at the same time. In the simulation part, CIFAR-10 (including 50k training images and 10k test images in 10 classes) is used to train VGG-19 and 20-layer, 32-layer, 44-layer and 56-layer CNN networks, and compare the difference between the optimal and non-optimal convolutional layer networks. The simulation results show that without optimisation, the accuracy of the test data drops from approximately 90% to about 80% as the number of network layers increases to 56 layers. However, the CNN with optimisation made it possible to maintain the test accuracy at more than 90%, and the number of network parameters could be reduced by nearly half or more. This shows that the proposed method can not only improve the network performance degradation caused by too many hidden convolutional layers, but also greatly reduce the use of the network’s computing resources.http://dx.doi.org/10.1080/09540091.2020.1841111convolutional neural networks (cnns)convolutional layer optimisationquantum evolutionary algorithm (qea) |
| spellingShingle | Tzyy-Chyang Lu CNN Convolutional layer optimisation based on quantum evolutionary algorithm Connection Science convolutional neural networks (cnns) convolutional layer optimisation quantum evolutionary algorithm (qea) |
| title | CNN Convolutional layer optimisation based on quantum evolutionary algorithm |
| title_full | CNN Convolutional layer optimisation based on quantum evolutionary algorithm |
| title_fullStr | CNN Convolutional layer optimisation based on quantum evolutionary algorithm |
| title_full_unstemmed | CNN Convolutional layer optimisation based on quantum evolutionary algorithm |
| title_short | CNN Convolutional layer optimisation based on quantum evolutionary algorithm |
| title_sort | cnn convolutional layer optimisation based on quantum evolutionary algorithm |
| topic | convolutional neural networks (cnns) convolutional layer optimisation quantum evolutionary algorithm (qea) |
| url | http://dx.doi.org/10.1080/09540091.2020.1841111 |
| work_keys_str_mv | AT tzyychyanglu cnnconvolutionallayeroptimisationbasedonquantumevolutionaryalgorithm |