Academic Journal
Convolutional neural network optimization using genetic algorithms
| Title: | Convolutional neural network optimization using genetic algorithms |
|---|---|
| Authors: | Reiling, Anthony Joseph |
| Source: | Graduate Theses and Dissertations |
| Publisher Information: | eCommons |
| Publication Year: | 2017 |
| Collection: | University of Dayton: eCommons |
| Subject Terms: | Genetic algorithms Data processing, Neural networks (Computer science), System design Data processing, Artificial Intelligence, Computer Engineering, Computer Science, deep learning hyper parameter genetic algorithm evolutionary computation convolutional neural network optimization CNN DL GA CIFAR10 |
| Description: | This thesis proposes the use of a genetic algorithm (GA) to optimize the accuracy of a convolutional neural network (CNN). The GA modifies the structure of the CNN such as the number of convolutional filters, strides, kernel size, nodes, learning parameters, etc. Each modification of the network is trained and evaluated. Mutation of evolved networks create more successful networks over multiple generations. The final evolved network is 4.77% more accurate than a network proposed in the previous literature. Additionally, the evolved network is 13.4% less computationally complex. |
| Document Type: | text |
| Language: | unknown |
| Relation: | https://ecommons.udayton.edu/graduate_theses/1337; http://rave.ohiolink.edu/etdc/view?acc_num=dayton1512662981172387 |
| Availability: | https://ecommons.udayton.edu/graduate_theses/1337 http://rave.ohiolink.edu/etdc/view?acc_num=dayton1512662981172387 |
| Rights: | Copyright © 2017, author |
| Accession Number: | edsbas.DEA2F439 |
| Database: | BASE |
| Description not available. |