Title:
ニューラルネットワーク処理装置、方法、および、プログラム
Document Type and Number:
Japanese Patent JP7384285
Kind Code:
B2
Abstract:
The 1 dimensional data generation means 92 generates 1 dimensional data, by setting the number of elements of each dimension other than predetermined one dimension to 1 based on multidimensional data corresponding to one input data. The number of elements reducing means 93 reduces the number of elements included in the 1 dimensional data. The copy means 95 generates multidimensional data, by copying the 1 dimensional data whose number of elements has been reduced multiple times. The convolution layer processing means 96 performs a convolution layer process with a filter size of 1×1 on the multidimensional data generated by the copy means 95. The element-wise product operation means 98 performs an element-wise product operation, based on the multidimensional data corresponding to one input data and multidimensional data generated by the above process.
Inventors:
Seiya Shibata
Application Number:
JP2022527284A
Publication Date:
November 21, 2023
Filing Date:
May 25, 2020
Export Citation:
Assignee:
NEC
International Classes:
G06N3/0464; G06F17/10; G06N3/0499; G06N3/10
Other References:
WANG, Qilong et al.,"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks",arXiv.org [online],arXiv:1910.03151v1,Cornell University,2019年10月,[検索日 2020.07.21], インターネット
Attorney, Agent or Firm:
Rock wall Fuyuki
Masato Shiokawa
Masato Shiokawa
Previous Patent: Trip plan generation device and trip plan generation method
Next Patent: Multidimensional data generation device, method, and program
Next Patent: Multidimensional data generation device, method, and program