Title:
NEURAL NETWORK CONFIGURATION PARAMETER TRAINING AND DEPLOYMENT METHOD AND APPARATUS FOR COPING WITH DEVICE MISMATCH
Document Type and Number:
WIPO Patent Application WO/2022/242471
Kind Code:
A1
Abstract:
A neural network (NN) configuration parameter training and deployment method and apparatus are disclosed. The method and the apparatus include searching for simulated attacked NN configuration parameters on a basis of NN configuration parameters, so that the attacked NN configuration parameters move in a direction of maximal divergence from an NN output result corresponding to the NN configuration parameters; taking a difference in an NN output result between the current NN configuration parameters and the attacked NN configuration parameters as a robustness loss function which serves as a part of a total loss function; and finally, optimizing the NN configuration parameters on a basis of the total loss function. Especially for sub-threshold and mixed-signal circuits with ultra-low power consumption, the solution can solve a problem of perturbations of configuration parameters caused by device mismatch, and achieve the technical effect of low-cost and high-efficiency deployment of parameters of NN accelerators.
Inventors:
RICHARD MUIR DYLAN (CH)
BUCHEL JULIAN (CH)
FABER FYNN (CH)
BUCHEL JULIAN (CH)
FABER FYNN (CH)
Application Number:
PCT/CN2022/091399
Publication Date:
November 24, 2022
Filing Date:
May 07, 2022
Export Citation:
Assignee:
CHENGDU SYNSENSE TECH CO LTD (CN)
International Classes:
G06N3/04
Foreign References:
| CN113313233A | 2021-08-27 | |||
| US20170316281A1 | 2017-11-02 | |||
| CN112035834A | 2020-12-04 | |||
| CN111898635A | 2020-11-06 | |||
| EP3754557A1 | 2020-12-23 | |||
| US20200234110A1 | 2020-07-23 |
Attorney, Agent or Firm:
PURPLEVINE INTELLECTUAL PROPERTY (SHENZHEN) CO., LTD. (CN)
Download PDF: