Title:
畳み込みニューラルネットワークの演算方法及び演算プログラム、情報処理装置
Document Type and Number:
Japanese Patent JP6750203
Kind Code:
B2
Abstract:
An computer-implemented information processing method for a convolutional neural network processing input data, includes: identifying, by a computer, for each of elements of a kernel used in convolution operation, input values to be multiplied by the respective elements in the convolution operation from among input values included in the input data; calculating a sum total of identified input values; calculating, for each of the elements of the kernel, a product of the sum total and the element; calculating an average of calculated products; and performing the convolution operation within the convolutional neural network based on the average of the calculated products.
Inventors:
Akihiko Kasagi
Application Number:
JP2015206157A
Publication Date:
September 02, 2020
Filing Date:
October 20, 2015
Export Citation:
Assignee:
富士通株式会社
International Classes:
G06F17/10; G06N3/10
Domestic Patent References:
| JP2006109490A | ||||
| JP2001175852A |
Other References:
岡谷 貴之,「Deep Learning(深層学習)」〔第4回〕,人工知能学会誌,日本,(一社)人工知能学会,2013年11月 1日,第28巻,第6号,pp.962-974
Attorney, Agent or Firm:
Kazuo Harada