# US 2022/0278696 A1 · Apparatus and method including neural network learning to detect and correct quantum errors

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

- Number: US 2022/0278696 A1
- Document ID: US20220278696A1
- Status: Published application
- Kind: A1
- Application number: 17/750,134
- Filed: 2022-05-20
- Published: 2022-09-01
- Earliest claimed: 2018-05-05
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: JUSTIN HOGABOAM; NARAYAN SRINIVASA
- Web page: https://patentgrep.com/patent/US20220278696A1

## CPC

- H03M 13/1575: {Direct decoding, e.g. by a direct determination of the error locator polynomial from syndromes and subsequent analysis or by matrix operations involving syndromes, e.g. for codes with a small minimum Hamming distance}
- G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G06N 3/065: Analogue means
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 10/70: Quantum error correction, detection or prevention, e.g. surface codes or magic state distillation
- H03M 13/611: {Specific encoding aspects, e.g. encoding by means of decoding}
- H03M 13/05: using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits {(H03M13/2906 takes precedence)}
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Apparatus and method for neural network learning to detect and correct quantum errors. For example, one embodiment of an apparatus comprises. For example, one embodiment of an apparatus comprises: a quantum processor comprising one or more data quantum bits (qbits) and one or more ancilla qbits; an error decoder to decode a state of at least one of the ancilla qbits to generate an error syndrome related to one or more qbit errors; a neural network to evaluate the error syndrome and to either identify a known corrective response for correcting the error or to perform unsupervised learning to identify a corrective response to the error syndrome.

## Claims

### Claim 1

A machine-readable medium having program code stored thereon which, when executed by a machine, causes the machine to perform the operations of:
identifying a first potential corrective response to the error syndrome based on an existing error correction model containing data related to known corrective responses for different error syndromes;
causing the first potential corrective response to be implemented; and
if the first potential corrective response corrects the error, then updating the error correction model to include data related to the new error.

### Claim 2 (depends on 1)

The method of claim 1 further comprising program code to cause the machine to perform the operation of:
selecting one or more additional potential corrective responses if the first potential corrective response does not correct the error until one is identified which corrects the error.

### Claim 3 (depends on 2)

The method of claim 2 further comprising program code to cause the machine to perform the operation of:
re-initializing the data qbits upon reaching a threshold number of attempts to identify a corrective response.
