US 12,217,163 B2
Methods and systems for budgeted and simplified training of deep neural networks
Yiwen Guo, Beijing (CN); Yuqing Hou, Beijing (CN); Anbang Yao, Beijing (CN); Dongqi Cai, Beijing (CN); Lin Xu, Beijing (CN); Ping Hu, Beijing (CN); Shandong Wang, Shanghai (CN); Wenhua Cheng, Shanghai (CN); Yurong Chen, Beijing (CN); and Libin Wang, Beijing (CN)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Sep. 22, 2023, as Appl. No. 18/371,934.
Application 18/371,934 is a continuation of application No. 17/584,216, filed on Jan. 25, 2022, granted, now 11,803,739.
Application 17/584,216 is a continuation of application No. 16/475,078, granted, now 11,263,490, issued on Mar. 1, 2022, previously published as PCT/CN2017/079719, filed on Apr. 7, 2017.
Prior Publication US 2024/0086693 A1, Mar. 14, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/62 (2022.01); G06F 18/21 (2023.01); G06F 18/213 (2023.01); G06F 18/214 (2023.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/063 (2023.01); G06N 3/08 (2023.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/94 (2022.01); G06V 20/00 (2022.01)
CPC G06N 3/063 (2013.01) [G06F 18/213 (2023.01); G06F 18/2148 (2023.01); G06F 18/217 (2023.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/94 (2022.01); G06V 10/955 (2022.01); G06V 20/00 (2022.01)] 14 Claims
OG exemplary drawing
 
1. A method for training a deep neural network (DNN), comprising:
receiving one or more input images;
generating a plurality of sub-images from each of the one or more input images;
training the DNN with batches of the plurality of sub-images to obtain a training result by adjusting weights of the DNN based on results from processing the batches of the sub-images.