Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324142375> ?p ?o ?g. }
- W4324142375 endingPage "36" @default.
- W4324142375 startingPage "1" @default.
- W4324142375 abstract "Convolutional neural networks (CNNs) are used in our daily life, including self-driving cars, virtual assistants, social network services, healthcare services, and face recognition, among others. However, deep CNNs demand substantial compute resources during training and inference. The machine learning community has mainly focused on model-level optimizations such as architectural compression of CNNs, whereas the system community has focused on implementation-level optimization. In between, various arithmetic-level optimization techniques have been proposed in the arithmetic community. This article provides a survey on resource-efficient CNN techniques in terms of model-, arithmetic-, and implementation-level techniques, and identifies the research gaps for resource-efficient CNN techniques across the three different level techniques. Our survey clarifies the influence from higher- to lower-level techniques based on our resource efficiency metric definition and discusses the future trend for resource-efficient CNN research." @default.
- W4324142375 created "2023-03-15" @default.
- W4324142375 creator A5014600847 @default.
- W4324142375 creator A5016123060 @default.
- W4324142375 creator A5019159365 @default.
- W4324142375 creator A5021983289 @default.
- W4324142375 creator A5056136163 @default.
- W4324142375 creator A5056162490 @default.
- W4324142375 creator A5078925783 @default.
- W4324142375 creator A5086758775 @default.
- W4324142375 creator A5089456682 @default.
- W4324142375 date "2023-07-13" @default.
- W4324142375 modified "2023-10-16" @default.
- W4324142375 title "Resource-Efficient Convolutional Networks: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques" @default.
- W4324142375 cites W1005811612 @default.
- W4324142375 cites W1487564550 @default.
- W4324142375 cites W1596397547 @default.
- W4324142375 cites W1604973310 @default.
- W4324142375 cites W1810296530 @default.
- W4324142375 cites W1849277567 @default.
- W4324142375 cites W1964480817 @default.
- W4324142375 cites W1985940938 @default.
- W4324142375 cites W1995341919 @default.
- W4324142375 cites W2002555321 @default.
- W4324142375 cites W2016354087 @default.
- W4324142375 cites W2016922062 @default.
- W4324142375 cites W2018636471 @default.
- W4324142375 cites W2040870580 @default.
- W4324142375 cites W2048266589 @default.
- W4324142375 cites W2064675550 @default.
- W4324142375 cites W2076118331 @default.
- W4324142375 cites W2077586448 @default.
- W4324142375 cites W2092608522 @default.
- W4324142375 cites W2102397476 @default.
- W4324142375 cites W2114988316 @default.
- W4324142375 cites W2117422822 @default.
- W4324142375 cites W2126182229 @default.
- W4324142375 cites W2130360162 @default.
- W4324142375 cites W2147800946 @default.
- W4324142375 cites W2150355110 @default.
- W4324142375 cites W2157239334 @default.
- W4324142375 cites W2165998261 @default.
- W4324142375 cites W2170510975 @default.
- W4324142375 cites W2172654076 @default.
- W4324142375 cites W2194775991 @default.
- W4324142375 cites W2289252105 @default.
- W4324142375 cites W2294370754 @default.
- W4324142375 cites W2300242332 @default.
- W4324142375 cites W2307193480 @default.
- W4324142375 cites W2316898842 @default.
- W4324142375 cites W2442974303 @default.
- W4324142375 cites W2489529491 @default.
- W4324142375 cites W2515287984 @default.
- W4324142375 cites W2518281301 @default.
- W4324142375 cites W2531409750 @default.
- W4324142375 cites W2549139847 @default.
- W4324142375 cites W2554302513 @default.
- W4324142375 cites W2563860341 @default.
- W4324142375 cites W2584616277 @default.
- W4324142375 cites W2604319603 @default.
- W4324142375 cites W2618530766 @default.
- W4324142375 cites W2623629680 @default.
- W4324142375 cites W2625457103 @default.
- W4324142375 cites W2729080111 @default.
- W4324142375 cites W2743322459 @default.
- W4324142375 cites W2750173518 @default.
- W4324142375 cites W2765234579 @default.
- W4324142375 cites W2766338242 @default.
- W4324142375 cites W2783525259 @default.
- W4324142375 cites W2783538964 @default.
- W4324142375 cites W2883030312 @default.
- W4324142375 cites W2883542588 @default.
- W4324142375 cites W2883780447 @default.
- W4324142375 cites W2886851211 @default.
- W4324142375 cites W2899818272 @default.
- W4324142375 cites W2913405856 @default.
- W4324142375 cites W2924943819 @default.
- W4324142375 cites W2935480346 @default.
- W4324142375 cites W2944557803 @default.
- W4324142375 cites W2950656546 @default.
- W4324142375 cites W2953915593 @default.
- W4324142375 cites W2956306874 @default.
- W4324142375 cites W2962677625 @default.
- W4324142375 cites W2962697884 @default.
- W4324142375 cites W2962821792 @default.
- W4324142375 cites W2962851801 @default.
- W4324142375 cites W2962861284 @default.
- W4324142375 cites W2962883027 @default.
- W4324142375 cites W2962883549 @default.
- W4324142375 cites W2963125010 @default.
- W4324142375 cites W2963145730 @default.
- W4324142375 cites W2963163009 @default.
- W4324142375 cites W2963363373 @default.
- W4324142375 cites W2963367920 @default.
- W4324142375 cites W2963387357 @default.
- W4324142375 cites W2963446712 @default.
- W4324142375 cites W2963594949 @default.
- W4324142375 cites W2963711383 @default.