Title:
ELECTRONIC CIRCUIT, NEURAL NETWORK, AND LEARNING METHOD OF NEURAL NETWORK
Document Type and Number:
Japanese Patent JP2021082130
Kind Code:
A
Abstract:
To swiftly obtain an optimum parameter of a neural network.SOLUTION: The electronic circuit includes quantum dots, a capacitance part, a current part, and a current adjustment part. In the circuit, the quantum dot includes a first electrode, a second electrode, and a third electrode; and the first electrode is connected to a first electric potential, the second electrode is connected to a first current source, and the third electrode is connected to a second current source. The current part functions to discharge the current from the second electrode or to supply the current to the second electrode. The current adjustment part adjusts the current on the current part and outputs a parameter used for adjustment of the current.SELECTED DRAWING: Figure 3
More Like This:
| JPH03294979 | SIGNAL PROCESSOR |
| JPH086915 | NEUROCOMPUTER AND ITS COMPUTING METHOD |
| JP2907486 | [Title of Invention] Neural network device |
Inventors:
SHINKAI GO
Application Number:
JP2019210549A
Publication Date:
May 27, 2021
Filing Date:
November 21, 2019
Export Citation:
Assignee:
HITACHI LTD
International Classes:
G06G7/60; B82Y10/00; G06N3/063; G06N99/00; H01L29/06
Domestic Patent References:
| JP2001313386A | 2001-11-09 | |||
| JP2000150862A | 2000-05-30 | |||
| JPH07176763A | 1995-07-14 | |||
| JPH07153977A | 1995-06-16 |
Foreign References:
| WO2018223037A1 | 2018-12-06 |
Attorney, Agent or Firm:
Aoritsu patent business corporation