Title:
CONVOLUTIONAL NEURAL NETWORK ORIENTED TWO-PHASE COEFFICIENT ADJUSTABLE ANALOG MULTIPLICATION CALCULATION CIRCUIT
Document Type and Number:
WIPO Patent Application WO/2021/056980
Kind Code:
A1
Abstract:
Disclosed is a convolutional neural network oriented two-phase coefficient adjustable analog multiplication calculation circuit, belonging to the technical field of calculation, reckoning, and counting. The multiplication calculation circuit comprises a current-mode network digital-to-analog conversion module, a two-phase coefficient adjustable analog multiplication array, a pipeline analog-to-digital conversion module, and a calculation unit control module. The multiplication calculation of a neural network layer is realized by using a discrete time circuit structure, and a signed multiplier design is newly added so as to provide positive control and negative control, such that the multiplication of signed bits can be realized, and a wider range of voltage amplitudes can be provided.
More Like This:
Inventors:
LIU BO (CN)
GONG YU (CN)
GE WEI (CN)
YANG JUN (CN)
SHI LONGXING (CN)
GONG YU (CN)
GE WEI (CN)
YANG JUN (CN)
SHI LONGXING (CN)
Application Number:
PCT/CN2020/079253
Publication Date:
April 01, 2021
Filing Date:
March 13, 2020
Export Citation:
Assignee:
UNIV SOUTHEAST (CN)
International Classes:
G06N3/04; G06F7/523; H03M1/66
Foreign References:
| CN110750231A | 2020-02-04 | |||
| CN109800876A | 2019-05-24 | |||
| CN107797962A | 2018-03-13 | |||
| CN107545305A | 2018-01-05 |
Attorney, Agent or Firm:
NANJING JINGWEI PATENT & TRADEMARK AGENCY CO., LTD (CN)
Download PDF: