# US 2026/0065044 A1 · Neuromorphic Computing Device and Operating Method Thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0065044 A1
- Document ID: US20260065044A1
- Status: Published application
- Kind: A1
- Application number: 19/381,911
- Filed: 2025-11-06
- Published: 2026-03-05
- Earliest claimed: 2020-04-23
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Youngnam Hwang
- Web page: https://patentgrep.com/patent/US20260065044A1

## CPC

- G06N 3/063: using electronic means
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/065: Analogue means
- G06N 3/08: Learning methods
- G11C 11/54: using elements simulating biological cells, e.g. neuron
- G11C 11/56: using storage elements with more than two stable states represented by steps, e.g. of voltage, current, phase, frequency
- G11C 13/0002: {using resistive RAM [RRAM] elements}
- G11C 13/0026: {Bit-line or column circuits}
- G11C 13/0028: {Word-line or row circuits}
- G11C 13/004: {Reading or sensing circuits or methods}
- G06N 3/045: Combinations of networks
- G11C 7/1006: {Data managing, e.g. manipulating data before writing or reading out, data bus switches or control circuits therefor}
- G11C 7/16: Storage of analogue signals in digital stores using an arrangement comprising analogue/digital [A/D] converters, digital memories and digital/analogue [D/A] converters
- G11C 13/003: {Cell access}
- G11C 2013/0045: {Read using current through the cell}
- G11C 2013/0054: {Read is performed on a reference element, e.g. cell, and the reference sensed value is used to compare the sensed value of the selected cell}
- G11C 2213/79: Array wherein the access device being a transistor
- H03M 1/12: Analogue/digital converters ({H03M1/001 – } H03M1/10 take precedence)
- H03M 1/361: {having a separate comparator and reference value for each quantisation level, i.e. full flash converter type}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G11C: STATIC STORES (semiconductor memory devices H10B)
- H03M: CODING; DECODING; CODE CONVERSION IN GENERAL (using fluidic means F15C4/00; optical analogue/digital converters G02F7/00; coding, decoding or code conversion, specially adapted for particular applications, see the relevant subclasses, e.g. G01D, G01R, G06F, G06T, G09G, G10L, G11B, G11C, H04B, H04L, H04M, H04N; ciphering or deciphering for cryptography or other purposes involving the need for secrecy G09C)

## Abstract

A neuromorphic computing device includes a first memory cell array comprising a plurality of resistive memory cells and configured to output a plurality of read currents through a plurality of bit lines or source lines; a second memory cell array comprising a plurality of reference resistive memory cells and configured to output at least one reference current through at least one reference bit line or at least one reference source line; a current-voltage converting circuit configured to output a plurality of signal voltages respectively corresponding to the plurality of read currents and output at least one reference voltage corresponding to the at least one reference current; and an analog-digital converting circuit configured to convert the plurality of signal voltages to a plurality of digital signals using the at least one reference voltage and output the plurality of digital signals.

## Claims

### Claim 1

(canceled)

### Claim 2

An operating method of a computing device comprising a first memory cell array and a second memory cell array, the first memory cell array comprising main resistive memory cells connected to a plurality of word lines, the second memory cell array comprising reference resistive memory cells connected to a plurality of reference word lines, and the method comprising:
activating selected word lines among the plurality of word lines according to element values of an input feature vector used in a computation of the computing device;
activating the plurality of reference word lines; and
using at least one reference voltage corresponding to at least one reference current output from the second memory cell array, outputting a plurality of digital signals by converting signal voltage values corresponding to read currents output from the first memory cell array to the plurality of digital signals according to the activating of the selected word lines.

### Claim 3 (depends on 2)

The method of claim 2, wherein each of the reference resistive memory cells comprises a same resistive material as a material of the main resistive memory cells.

### Claim 4 (depends on 2)

The method of claim 2, wherein a number of reference bit lines connected to the second memory cell array corresponds to a number obtained by subtracting 1 from 2 raised to a power of a number of bits of each of the plurality of digital signals.

### Claim 5 (depends on 2)

The method of claim 2, wherein the at least one reference voltage equally quantizes an operating voltage range of an analog-to-digital converting circuit in the computing device.

### Claim 6 (depends on 2)

The method of claim 2, wherein the at least one reference voltage unequally quantizes an operating voltage range of an analog-to-digital converting circuit in the computing device such that a quantization interval adjacent to a center of the operating voltage range is narrower than a quantization interval adjacent to a side of the operating voltage range.

### Claim 7 (depends on 2)

The method of claim 2, wherein a load resistor having a resistance value between a low resistance state and a high resistance state of the reference resistive memory cells is connected between a reference source line of the second memory cell array and a ground node during the converting of the signal voltage values.

### Claim 8 (depends on 2)

The method of claim 2, wherein the computing device performs neuromorphic operations using the plurality of digital signals.

### Claim 9 (depends on 8)

The method of claim 8, wherein the at least one reference voltage unequally quantizes an operating voltage range of an analog-to-digital converting circuit in the computing device such that a quantization interval adjacent to a center of the operating voltage range is narrower than a quantization interval adjacent to a side of the operating voltage range.

### Claim 10

A computing device that converts current output from a crossbar array to a digital signal, the computing device comprising:
a first memory cell array comprising a plurality of resistive memory cells respectively connected to a plurality of word lines;
a second memory cell array comprising a plurality of reference resistive memory cells disposed in a region where a plurality of reference word lines intersect with a plurality of reference bit lines and having a same resistive material as the plurality of resistive memory cells; and
a word line driver configured to drive the plurality of word lines and the plurality of reference word lines and activate all of the plurality of reference word lines during an operation of the computing device,
wherein a number of reference bit lines is a same as a number obtained by subtracting 1 from a square of a number of bits of the digital signal.

### Claim 11 (depends on 10)

The computing device of claim 10, wherein the computing device performs neuromorphic operations comprising at least one of an accumulation operation or a summation operation using the digital signal.

### Claim 12 (depends on 10)

The computing device of claim 10, comprising:
a current-to-voltage converting circuit configured to output a plurality of signal voltages respectively corresponding to a plurality of read currents output from the first memory cell array and output at least one reference voltage corresponding to at least one reference current output from the second memory cell array; and
an analog-to-digital converting circuit configured to convert the plurality of signal voltages to a plurality of digital signals using the at least one reference voltage and output the plurality of digital signals.

### Claim 13 (depends on 12)

The computing device of claim 12, wherein the at least one reference voltage equally quantizes an operating voltage range of the analog-to-digital converting circuit.

### Claim 14 (depends on 12)

The computing device of claim 12, wherein the analog-to-digital converting circuit comprises
a comparison circuit configured to output at least one comparison signal by comparing each of the plurality of signal voltages with the at least one reference voltage, and
an encoding circuit configured to output the digital signals based on the at least one comparison signal.

### Claim 15

A computing circuit comprising:
a first memory cell array having a plurality of memory cells each connected between a respective one of a first plurality of word lines and a respective one of a second plurality of bit lines; and
a second memory cell array having a plurality of reference memory cells each connected between a respective one of a first plurality of reference word lines and a respective one of a third plurality of reference bit lines, wherein the third plurality is a number of bits per memory cell, minus one, raised to a power of a number of states per bit.

### Claim 16 (depends on 15)

The computing circuit of claim 15, comprising:
a current-to-voltage circuit coupled to the first and second memory cell arrays;
an analog-to-digital circuit coupled to the current-to-voltage circuit; and
an adder circuit coupled to the analog-to-digital circuit.

### Claim 17 (depends on 15)

The computing circuit of claim 15, comprising:
a word line driver circuit configured to drive a respective one of the first plurality of word lines and a respective one of the first plurality of reference word lines substantially simultaneously,
wherein the plurality of memory cells comprises a substantially same cell material as the plurality of reference memory cells, and the plurality of memory cells has at least one of substantially same temperature characteristics or substantially same time decay characteristics as the plurality of reference memory cells.

### Claim 18 (depends on 15)

The computing circuit of claim 15,
wherein the plurality of memory cells and the plurality of reference memory cells each comprise resistive memory cells, and
wherein values stored by the plurality of memory cells correspond to weights to be applied to incoming signals within the computing circuit.

### Claim 19 (depends on 15)

The computing circuit of claim 15,
wherein the first and second memory cell arrays comprise at least one of a phase change random-access memory (PRAM) cell, a resistance random-access memory (RRAM) cell, a magnetic random-access memory (MRAM) cell, or a ferroelectric random-access memory (FRAM) cell.

### Claim 20 (depends on 15)

The computing circuit of claim 15, wherein the computing circuit performs neuromorphic operations comprising at least one of an accumulation operation or a summation operation based on digital signals generated from the first memory cell array.

### Claim 21 (depends on 15)

The computing circuit of claim 15, comprising a load resistor connected between a reference source line of the second memory cell array and a ground node, the load resistor having a resistance value between a low resistance state and a high resistance state of the reference memory cells.
