A neural network architecture that applies small, shared filters across an input, most often an image, to detect local patterns such as edges and textures regardless of where in the input they appear; the standard architecture behind most modern image recognition.
Facts
Core PrincipleFeatures are learned through filter (kernel) optimization, with many neurons sharing the same filter. 1 Connections
In Field
Invented
Yann LeCun developed the convolutional neural network architecture, demonstrated in his LeNet work on handwritten digit recognition in the late 1980s and 1990s.
Sources
1. Convolutional neural network - Wikipedia
Section: Neocognitron, origin of the trainable CNN architecture
introduced by Fukushima in 1980
Lead paragraph
A distinguishing feature of CNNs is that many neurons can share the same filter.
View the SourceReader Challenges (0)
No disputes yet. Spotted an error or a better source? Open the first one.
Sign in to dispute this or suggest a correction.