IP Library Granted Patent US 12,468,508
Granted Patent B2
US 12,468,508 · App. 18/761,402 · Granted Nov 11, 2025

Neuromorphic device and driving method thereof

Inventors: Sungmeen Myung (Suwon-si, KR); Sangjoon Kim (Hwaseong-si, KR); Seungchul Jung (Suwon-si, KR)
Assignee: Samsung Electronics Co., Ltd.
G06F7/5443G01R19/0046G06F13/4022G06F13/4282G06N3/04G11C11/161G11C11/1673G11C11/54
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,468,508
App. No.
18/761,402
Granted
Nov 11, 2025
Kind
B2
Abstract

A neuromorphic device includes a plurality of resistor lines, each comprising a plurality of resistors that are serially connected to each other; one or more current sources configured to control a current flowing in each of the resistor lines to a respective current value; a plurality of capacitors configured to be electrically connected to each of the resistor lines and to sample respective voltage of each of the resistor lines representing results of neuromorphic operations; and a switch configured to connect the plurality of the capacitors in parallel after the sampling the respective voltage of each of the resistor lines, to output a sum of the results of neuromorphic operations.

Claims (31)

1 . A neuromorphic device comprising:

a plurality of resistor lines, each comprising a plurality of resistors that are serially connected to each other;

one or more current sources configured to control a current flowing in each of the resistor lines to a respective current value;

a plurality of capacitors configured to be electrically connected to each of the resistor lines and to sample respective voltage of each of the resistor lines representing results of neuromorphic operations; and

a switch configured to connect the plurality of the capacitors in parallel after the sampling the respective voltage of each of the resistor lines, to output a sum of the results of neuromorphic operations.

2 . The neuromorphic device of claim 1 , further comprising a voltage meter configured to measure a voltage difference between both terminals of each of the capacitors in a configuration in which the capacitors are connected in parallel.

3 . The neuromorphic device of claim 1 , wherein the one or more current sources comprise one or more current sources that are respectively connected to the resistor lines.

4 . The neuromorphic device of claim 1 , further comprising a controller configured to apply inputs and weights to the plurality of the resistors.

5 . The neuromorphic device of claim 1 , wherein the one or more current sources are configured to control a current flowing in each of the resistor lines to a same current value.

6 . The neuromorphic device of claim 4 , wherein the controller is configured to independently control inputs to be applied to the plurality of the resistors.

7 . The neuromorphic device of claim 1 , wherein each of the capacitors has a same capacitance.

8 . The neuromorphic device of claim 1 , further comprising:

a plurality of switches each disposed between each of the capacitors and each of the resistor lines.

9 . The neuromorphic device of claim 1 , wherein each of the resistors comprises a magnetic memory device having a plurality of resistance values.

10 . The neuromorphic device of claim 1 , wherein terminals for each of the capacitors are electrically connected to each other.

11 . The neuromorphic device of claim 1 , wherein each of the resistors comprises at least two variable resistors that are connected in parallel to each other and switches that are respectively serially connected to the variable resistors.

12 . The neuromorphic device of claim 11 , wherein each of the resistors comprises one variable resistor that has a first resistance value and another resistor that has a second resistance value.

13 . A method of driving a neuromorphic device, the method comprising:

applying a current having a current value to each of a plurality of resistor lines, the plurality of resistor lines each comprising a plurality of resistors that are serially connected;

sampling respective voltage of each of the resistor lines by using a plurality of capacitors each connected to each of the resistor lines, the sampled respective voltage representing results of neuromorphic operations; and

outputting a sum of the results of neuromorphic operations by switching a connection of the capacitors in parallel after the sampling the respective voltage of each of the resistor lines.

14 . The method of claim 13 , further comprising calculating a sum of multiplications of inputs and weights applied to the resistors from the sum of the results.

15 . An electronic system comprising:

a neural network device comprising a neuromorphic device; and

a central processing unit (CPU) configured to control a function of the neural network device,

wherein the neuromorphic device comprises:

a plurality of resistor lines, each comprising a plurality of resistors that are serially connected to each other;

one or more current sources configured to control a current flowing in each of the resistor lines to a respective current value;

a plurality of capacitors configured to be electrically connected to each of the resistor lines and to sample respective voltage of each of the resistor lines representing results of neuromorphic operations; and

a switch configured to connect the plurality of the capacitors in parallel after the sampling the respective voltage of each of the resistor lines, to output a sum of the results of neuromorphic operations.

16 . The electronic system of claim 15 , wherein each voltage of the capacitors represents a result of a multiply-and-accumulate (MAC) operation involving respective inputs, to or within a neural network, and corresponding resistors that have resistances respectively representing parameters of the neural network.

Priority Claims (1)
KR 10-2020-0036433 · Mar 25, 2020 · national
Continuity (2)
Continuation 17075774 · Oct 21, 2020
Related Publication 20240354059A1 · Oct 24, 2024
References Cited (33)
US 10417460B1 · Youssefi · 2019 [cited by applicant]
US 10819303B1 · Park et al. · 2020 [cited by applicant]
US 20160371582A1 · Eleftheriou et al. · 2016 [cited by applicant]
US 20180253643A1 · Buchanan et al. · 2018 [cited by applicant]
US 20180300618A1 · Obradovic et al. · 2018 [cited by applicant]
US 20190012593A1 · Obradovic et al. · 2019 [cited by applicant]
US 20190019538A1 · Li et al. · 2019 [cited by applicant]
US 20190080230A1 · Hatcher et al. · 2019 [cited by applicant]
US 20190088309A1 · Li et al. · 2019 [cited by applicant]
US 20190286419A1 · Lin et al. · 2019 [cited by applicant]
US 20190286976A1 · Tran et al. · 2019 [cited by applicant]
US 20190385049A1 · Yang et al. · 2019 [cited by applicant]
US 20200202204A1 · Kouno et al. · 2020 [cited by applicant]
US 20210117769A1 · Oberadovic et al. · 2021 [cited by applicant]
CN 105389279A · 2016 [cited by applicant]
CN 107688366A · 2018 [cited by applicant]
CN 108734271A · 2018 [cited by applicant]
CN 109214510A · 2019 [cited by applicant]
CN 109492187A · 2019 [cited by applicant]
JP 2009282782A · 2009 [cited by applicant]
KR 1020150017047A · 2015 [cited by applicant]
KR 1020180116094A · 2018 [cited by applicant]
KR 1020190029406A · 2019 [cited by applicant]
WO WO2017105514A1 · 2017 [cited by applicant]
WO WO2019049741A1 · 2019 [cited by applicant]
Wei Yi et al., “Biological Plausibility and Stochasticity in Scalable VO2 Active Memristor Neurons”, arxiv.org, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY 14853, (Sep. 20, 2018), XP081085… [cited by applicant]
Shimeng Yu et al., “An Electronic Synapse Device Based on Metal Oxide Resistive Switching Memory for Neuromorphic Computation”, IEEE Transactions on Electron Devices, IEEE, USA, (Aug. 1, 2011), vol. 58, No. 8, ISSN 0018… [cited by applicant]
Li, Yunning et al., “Analog Computing Using 1T1R Crossbar Arrays”, Masters Theses, University of Massachusetts Amherst, Feb. 2018, XP055860081, (81 pages in English). [cited by applicant]
Extended European search report issued on Jan. 12, 2022, in counterpart European Patent Application No. 21154932.4 (10 pages in English). [cited by applicant]
Korean Office Action issued on Nov. 21, 2024 in corresponding Korean Patent Application No. 10-2020-0036433. (6 pages in English and 6 pages in Korean). [cited by applicant]
Chinese Office Action issued on Mar. 29, 2025, in corresponding Chinese Patent Application No. 202011399511.7. (27pages in English, 15pages in Chinese). [cited by applicant]
Japanese Office Action issued on Feb. 12, 2025, in corresponding Japanese Patent Application No. 2021-036434. (3pages in English, 3pages in Japanese). [cited by applicant]
Pingping, Chen, et al., “Design and Implementation of Temperature Measuring Instrument Based on PT100”, Computer Measurement & Control, 1671-4598, 03-1041-04, 23,3, Jan. 9, 2015. (pp. 1041-1044). [cited by applicant]