{"id":132001,"date":"2022-07-25T18:48:11","date_gmt":"2022-07-25T09:48:11","guid":{"rendered":"http:\/\/192.249.19.202\/?post_type=ai-in-circuit&#038;p=132001"},"modified":"2026-04-05T18:06:48","modified_gmt":"2026-04-05T09:06:48","slug":"energy-efficient-cnn-personalized-training-by-adaptive-data-reformation","status":"publish","type":"ai-in-circuit","link":"http:\/\/ee.presscat.kr\/en\/ai-in-circuit\/energy-efficient-cnn-personalized-training-by-adaptive-data-reformation\/","title":{"rendered":"Energy-Efficient CNN Personalized Training by Adaptive Data Reformation"},"content":{"rendered":"<p>Title : Energy-Efficient CNN Personalized Training by Adaptive Data Reformation<\/p>\n<p>&nbsp;<\/p>\n<p>Author: Youngbeom Jung, Hyeonuk Kim, Seungkyu Choi, Jaekang Shin, Lee-Sup Kim<\/p>\n<p>&nbsp;<\/p>\n<p>Journal : IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems<\/p>\n<p>&nbsp;<\/p>\n<p>Abstract : To adopt deep neural networks in resource constrained edge devices, various energy-and memory-efficient embedded accelerators have been proposed. However, most off-the-shelf networks are well-trained with vast amounts of data, but unexplored users\u2019 data or accelerator\u2019s constraints can lead to unexpected accuracy loss. Therefore, a network adaptation suitable for each user and device is essential to make a high confidence prediction in given environment. We propose simple but efficient data reformation methods that can effectively reduce the communication cost with off-chip memory during the adaptation. Our proposal utilizes the data\u2019s zero-centered distribution and spatial correlation to concentrate the sporadically spread bit-level zeros to the units of value. Consequently, we reduced communication volume by up to 55.6% per task with an area overhead of 0.79% during the personalization training.<\/p>\n<p><img fetchpriority=\"high\" decoding=\"async\" class=\"alignnone size-full wp-image-132002\" src=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/07\/\uae40\uc774\uc12d3.png\" alt=\"\" width=\"1218\" height=\"766\" title=\"\" srcset=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/07\/\uae40\uc774\uc12d3.png 1218w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/07\/\uae40\uc774\uc12d3-300x189.png 300w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/07\/\uae40\uc774\uc12d3-1024x644.png 1024w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/07\/\uae40\uc774\uc12d3-768x483.png 768w\" sizes=\"(max-width: 1218px) 100vw, 1218px\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>681<\/p>\n","protected":false},"featured_media":0,"template":"","class_list":["post-132001","ai-in-circuit","type-ai-in-circuit","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/ai-in-circuit\/132001","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/ai-in-circuit"}],"about":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/types\/ai-in-circuit"}],"wp:attachment":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media?parent=132001"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}