dc.contributor.author | Williams, David P. | |
dc.date.accessioned | 2019-06-19T12:18:19Z | |
dc.date.available | 2019-06-19T12:18:19Z | |
dc.date.issued | 2019/06 | |
dc.identifier.govdoc | CMRE-PR-2019-081 | en_US |
dc.identifier.uri | http://hdl.handle.net/20.500.12489/821 | |
dc.description.abstract | Deep convolutional neural networks (CNNs) are developed to perform underwater target classification in synthetic aperture sonar (SAS) imagery. The deep networks are trained using a huge database of sonar data collected at sea in various geographical locations. The value of CNN ensemble averaging is highlighted, and the feasibility of sonar sensor transfer learning with CNNs is also demonstrated. An analysis that seeks to demystify deep learning suggests tools for understanding how and why the trained CNNs work so well. | en_US |
dc.format | 5 p. : ill. ; digital, PDF file | |
dc.language.iso | en | en_US |
dc.publisher | CMRE | en_US |
dc.source | In: Proceedings of the 4th Underwater Acoustics Conference, Skiathos, Greece, 3-8 September 2017, pp. 513-520. | en_US |
dc.subject | Synthetic Aperture Sonar (SAS) | en_US |
dc.subject | Sonar images | en_US |
dc.subject | Image processing | en_US |
dc.subject | Neural networks (Computer science) | en_US |
dc.subject | Convolutions (Mathematics) | en_US |
dc.subject | Machine learning | en_US |
dc.subject | Target classification | en_US |
dc.subject | Mine countermeasures (MCM) | en_US |
dc.title | Demystifying deep convolutional neural networks for sonar image classification | en_US |
dc.type | Reprint (PR) | en_US |
dc.type | Papers and Articles | en_US |