Title:
NEURAL NETWORK MODEL CONVERSION DEVICE AND METHOD
Document Type and Number:
WIPO Patent Application WO/2022/264252
Kind Code:
A1
Abstract:
A division position determination means 701 determines a division position in a weighting value group of at least one layer included in an applied neural network model, the weighting value group being configured such that kernels obtained by aligning at least one or more weighting values in a channel direction are aligned in a kernel direction. A division means 702 divides the weighting value group at the division position, and thereby obtains a plurality of weighting value groups. A combined layer adding means 703 adds a combined layer in which pieces of output data, respectively obtained by calculating data input into the layer and each weighting value group after the division, are combined to form one output data. Furthermore, when a proportion of the number of weighting values which are 0 to the number of weighting values included in a weighting value group is used as a sparse degree, the division position determination means 701 determines a division position in the weighting value group prior to division such that at least one of the weighting value groups after the division has a sparse degree of a prescribed value or higher.
Inventors:
SHIBATA SEIYA (JP)
Application Number:
PCT/JP2021/022649
Publication Date:
December 22, 2022
Filing Date:
June 15, 2021
Export Citation:
Assignee:
NEC CORP (JP)
International Classes:
G06N3/04
Domestic Patent References:
| WO2019082859A1 | 2019-05-02 |
Foreign References:
| JP2021077342A | 2021-05-20 |
Attorney, Agent or Firm:
IWAKABE Fuyuki et al. (JP)
Download PDF:
Previous Patent: WATER PURIFICATION DEVICE
Next Patent: RISK ANALYSIS DEVICE AND METHOD AND COMPUTER-READABLE MEDIUM
Next Patent: RISK ANALYSIS DEVICE AND METHOD AND COMPUTER-READABLE MEDIUM