Convolution

A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the part of the input it is on, then summing the results into an output. Intuitively, a convolution allows for weight sharing - reducing the number of effective parameters - and image translation (allowing for the same feature to be detected in different parts of the input space). Source: https://arxiv.org/pdf/1603.07285.pdf
相关学科: CVMLImage ClassificationU-NetObject DetectionTransfer LearningResNetSemantic SegmentationAlexNetSuper-Resolution

学科讨论

讨论Icon

暂无讨论内容,你可以

推荐文献

按被引用数

学科管理组

暂无学科课代表,你可以申请成为课代表

重要学者

Yoshua Bengio

429868 被引用,1063 篇论文

Geoffrey E. Hinton

345738 被引用,408 篇论文

Yi Chen

267689 被引用,4684 篇论文

David Haussler

210533 被引用,548 篇论文

Kaiming He

202871 被引用,125 篇论文

Karl J. Friston

198421 被引用,1357 篇论文

Andrew Zisserman

195560 被引用,885 篇论文

Richard Durbin

189768 被引用,339 篇论文

Jian Sun

179895 被引用,332 篇论文

Yann LeCun

175383 被引用,366 篇论文