https://scholars.lib.ntu.edu.tw/handle/123456789/581342
標題: | Unifying and merging well-trained deep neural networks for inference stage | 作者: | Chou Y.-M Chan Y.-M Lee J.-H Chiu C.-Y CHU-SONG CHEN |
關鍵字: | Artificial intelligence; Network architecture; Compact model; General architectures; Inference stages; Resource-limited devices; System development; Training overhead; Unified Modeling; Deep neural networks | 公開日期: | 2018 | 卷: | 2018-July | 起(迄)頁: | 2049-2056 | 來源出版物: | IJCAI International Joint Conference on Artificial Intelligence | 摘要: | We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks and merges them into a unified model by sharing the representative codes of weights. The shared weights are further re-trained to fine-tune the performance of the merged model. The proposed method effectively produces a compact model that may run original tasks simultaneously on resource-limited devices. As it preserves the general architectures and leverages the co-used weights of well-trained networks, a substantial training overhead can be reduced to shorten the system development time. Experimental results demonstrate a satisfactory performance and validate the effectiveness of the method. ? 2018 International Joint Conferences on Artificial Intelligence. All right reserved. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85055700097&doi=10.24963%2fijcai.2018%2f283&partnerID=40&md5=bf14aa787bff1d9ddf711342c62b7b74 https://scholars.lib.ntu.edu.tw/handle/123456789/581342 |
ISSN: | 10450823 | DOI: | 10.24963/ijcai.2018/283 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。