Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972566708> ?p ?o ?g. }
- W2972566708 endingPage "C09011" @default.
- W2972566708 startingPage "C09011" @default.
- W2972566708 abstract "Convolutional neural networks (CNNs) have found applications in many image processing tasks, such as feature extraction, image classification, and object recognition. It has also been shown that the inverse of CNNs, so-called deconvolutional neural networks, can be used for inverse problems such as plasma tomography. In essence, plasma tomography consists in reconstructing the 2D plasma profile on a poloidal cross-section of a fusion device, based on line-integrated measurements from multiple radiation detectors. Since the reconstruction process is computationally intensive, a deconvolutional neural network trained to produce the same results will yield a significant computational speedup, at the expense of a small error which can be assessed using different metrics. In this work, we discuss the design principles behind such networks, including the use of multiple layers, how they can be stacked, and how their dimensions can be tuned according to the number of detectors and the desired tomographic resolution for a given fusion device. We describe the application of such networks at JET and COMPASS, where at JET we use the bolometer system, and at COMPASS we use the soft X-ray diagnostic based on photodiode arrays." @default.
- W2972566708 created "2019-09-19" @default.
- W2972566708 creator A5000285332 @default.
- W2972566708 creator A5000390042 @default.
- W2972566708 creator A5000468844 @default.
- W2972566708 creator A5000832312 @default.
- W2972566708 creator A5000842219 @default.
- W2972566708 creator A5000895866 @default.
- W2972566708 creator A5000955962 @default.
- W2972566708 creator A5000986786 @default.
- W2972566708 creator A5001052232 @default.
- W2972566708 creator A5001055810 @default.
- W2972566708 creator A5001184279 @default.
- W2972566708 creator A5001303814 @default.
- W2972566708 creator A5001385515 @default.
- W2972566708 creator A5001418286 @default.
- W2972566708 creator A5001553512 @default.
- W2972566708 creator A5001629038 @default.
- W2972566708 creator A5001781095 @default.
- W2972566708 creator A5001953487 @default.
- W2972566708 creator A5002014430 @default.
- W2972566708 creator A5002056153 @default.
- W2972566708 creator A5002204160 @default.
- W2972566708 creator A5002220668 @default.
- W2972566708 creator A5002227414 @default.
- W2972566708 creator A5002290299 @default.
- W2972566708 creator A5002429943 @default.
- W2972566708 creator A5002446373 @default.
- W2972566708 creator A5002513091 @default.
- W2972566708 creator A5002843357 @default.
- W2972566708 creator A5003011909 @default.
- W2972566708 creator A5003076029 @default.
- W2972566708 creator A5003132003 @default.
- W2972566708 creator A5003243575 @default.
- W2972566708 creator A5003251605 @default.
- W2972566708 creator A5003281329 @default.
- W2972566708 creator A5003281971 @default.
- W2972566708 creator A5003473626 @default.
- W2972566708 creator A5003502659 @default.
- W2972566708 creator A5003592115 @default.
- W2972566708 creator A5003662135 @default.
- W2972566708 creator A5003677333 @default.
- W2972566708 creator A5003695814 @default.
- W2972566708 creator A5003695817 @default.
- W2972566708 creator A5003701879 @default.
- W2972566708 creator A5003875003 @default.
- W2972566708 creator A5003923565 @default.
- W2972566708 creator A5004072849 @default.
- W2972566708 creator A5004232924 @default.
- W2972566708 creator A5004328482 @default.
- W2972566708 creator A5004337021 @default.
- W2972566708 creator A5004378143 @default.
- W2972566708 creator A5004406942 @default.
- W2972566708 creator A5004421657 @default.
- W2972566708 creator A5004445528 @default.
- W2972566708 creator A5004639515 @default.
- W2972566708 creator A5004660959 @default.
- W2972566708 creator A5004660972 @default.
- W2972566708 creator A5004682876 @default.
- W2972566708 creator A5004830987 @default.
- W2972566708 creator A5004837654 @default.
- W2972566708 creator A5004894871 @default.
- W2972566708 creator A5004953459 @default.
- W2972566708 creator A5004957119 @default.
- W2972566708 creator A5004965554 @default.
- W2972566708 creator A5005107897 @default.
- W2972566708 creator A5005110607 @default.
- W2972566708 creator A5005193089 @default.
- W2972566708 creator A5005203976 @default.
- W2972566708 creator A5005339214 @default.
- W2972566708 creator A5005343901 @default.
- W2972566708 creator A5005376298 @default.
- W2972566708 creator A5005383713 @default.
- W2972566708 creator A5005414173 @default.
- W2972566708 creator A5005622431 @default.
- W2972566708 creator A5005632786 @default.
- W2972566708 creator A5005929273 @default.
- W2972566708 creator A5005956036 @default.
- W2972566708 creator A5006181549 @default.
- W2972566708 creator A5006666493 @default.
- W2972566708 creator A5006766178 @default.
- W2972566708 creator A5006835507 @default.
- W2972566708 creator A5006872245 @default.
- W2972566708 creator A5006883893 @default.
- W2972566708 creator A5006898127 @default.
- W2972566708 creator A5007003558 @default.
- W2972566708 creator A5007089855 @default.
- W2972566708 creator A5007196518 @default.
- W2972566708 creator A5007348092 @default.
- W2972566708 creator A5007378949 @default.
- W2972566708 creator A5007399158 @default.
- W2972566708 creator A5007438849 @default.
- W2972566708 creator A5007639331 @default.
- W2972566708 creator A5007695310 @default.
- W2972566708 creator A5007698148 @default.
- W2972566708 creator A5007702129 @default.
- W2972566708 creator A5007760954 @default.
- W2972566708 creator A5007770235 @default.