Title:
マルチフィーディングを適用した学習方法及び学習装置並びにそれを利用したテスト方法及びテスト装置
Document Type and Number:
Japanese Patent JP6935939
Kind Code:
B2
Abstract:
A learning method for a CNN (Convolutional Neural Network) capable of encoding at least one training image with multiple feeding layers, wherein the CNN includes a 1st to an n-th convolutional layers, which respectively generate a 1st to an n-th main feature maps by applying convolution operations to the training image, and a 1st to an h-th feeding layers respectively corresponding to h convolutional layers (1≤h≤ (n-1)) is provided. The learning method includes steps of: a learning device instructing the convolutional layers to generate the 1st to the n-th main feature maps, wherein the learning device instructs a k-th convolutional layer to acquire a (k-1)-th main feature map and an m-th sub feature map, and to generate a k-th main feature map by applying the convolution operations to the (k-1)-th integrated feature map generated by integrating the (k-1)-th main feature map and the m-th sub feature map.
More Like This:
Inventors:
Ken Katsura
Kim
Kim Taoru
Gold crane
Southern cloud
Husband Shou
Akira Satoshi
Lu Dongyuan
Willow universe
Yasuo Zhang
Chung
Various models
Zhao Kotatsu
Kim
Kim Taoru
Gold crane
Southern cloud
Husband Shou
Akira Satoshi
Lu Dongyuan
Willow universe
Yasuo Zhang
Chung
Various models
Zhao Kotatsu
Application Number:
JP2019163897A
Publication Date:
September 15, 2021
Filing Date:
September 09, 2019
Export Citation:
Assignee:
Stradvision,Inc.
International Classes:
G06N3/08
Domestic Patent References:
JP2019101519A | ||||
JP2018124813A |
Foreign References:
CN107958246A |
Attorney, Agent or Firm:
Tadashige Ito
Tadahiko Ito
Shinsuke Onuki
Tadahiko Ito
Shinsuke Onuki