Trainability of Dissipative Perceptron-Based Quantum Neural Networks

Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. He...

Full description

Saved in:
Bibliographic Details
Published in:Physical review letters Vol. 128; no. 18; p. 180505
Main Authors: Sharma, Kunal, Cerezo, M., Cincio, Lukasz, Coles, Patrick J.
Format: Journal Article
Language:English
Published: United States American Physical Society (APS) 06.05.2022
Subjects:
ISSN:0031-9007, 1079-7114, 1079-7114
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. Here, we analyze the gradient scaling (and hence the trainability) for a recently proposed architecture that we call dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer's output. We find that DQNNs can exhibit barren plateaus, i.e., gradients that vanish exponentially in the number of qubits. Moreover, we provide quantitative bounds on the scaling of the gradient for DQNNs under different conditions, such as different cost functions and circuit depths, and show that trainability is not always guaranteed. Our work represents the first rigorous analysis of the scalability of a perceptron-based QNN.
AbstractList Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. Here, we analyze the gradient scaling (and hence the trainability) for a recently proposed architecture that we call dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer's output. We find that DQNNs can exhibit barren plateaus, i.e., gradients that vanish exponentially in the number of qubits. Moreover, we provide quantitative bounds on the scaling of the gradient for DQNNs under different conditions, such as different cost functions and circuit depths, and show that trainability is not always guaranteed. Our work represents the first rigorous analysis of the scalability of a perceptron-based QNN.
Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. Here, we analyze the gradient scaling (and hence the trainability) for a recently proposed architecture that we call dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer’s output. We find that DQNNs can exhibit barren plateaus, i.e., gradients that vanish exponentially in the number of qubits. Moreover, we provide quantitative bounds on the scaling of the gradient for DQNNs under different conditions, such as different cost functions and circuit depths, and show that trainability is not always guaranteed. Here our work represents the first rigorous analysis of the scalability of a perceptron-based QNN.
Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. Here, we analyze the gradient scaling (and hence the trainability) for a recently proposed architecture that we call dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer's output. We find that DQNNs can exhibit barren plateaus, i.e., gradients that vanish exponentially in the number of qubits. Moreover, we provide quantitative bounds on the scaling of the gradient for DQNNs under different conditions, such as different cost functions and circuit depths, and show that trainability is not always guaranteed. Our work represents the first rigorous analysis of the scalability of a perceptron-based QNN.Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. Here, we analyze the gradient scaling (and hence the trainability) for a recently proposed architecture that we call dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer's output. We find that DQNNs can exhibit barren plateaus, i.e., gradients that vanish exponentially in the number of qubits. Moreover, we provide quantitative bounds on the scaling of the gradient for DQNNs under different conditions, such as different cost functions and circuit depths, and show that trainability is not always guaranteed. Our work represents the first rigorous analysis of the scalability of a perceptron-based QNN.
ArticleNumber 180505
Author Cincio, Lukasz
Cerezo, M.
Coles, Patrick J.
Sharma, Kunal
Author_xml – sequence: 1
  givenname: Kunal
  orcidid: 0000-0003-3132-1088
  surname: Sharma
  fullname: Sharma, Kunal
– sequence: 2
  givenname: M.
  orcidid: 0000-0002-2757-3170
  surname: Cerezo
  fullname: Cerezo, M.
– sequence: 3
  givenname: Lukasz
  orcidid: 0000-0002-6758-4376
  surname: Cincio
  fullname: Cincio, Lukasz
– sequence: 4
  givenname: Patrick J.
  surname: Coles
  fullname: Coles, Patrick J.
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35594093$$D View this record in MEDLINE/PubMed
https://www.osti.gov/servlets/purl/1992248$$D View this record in Osti.gov
BookMark eNqFkU1P3DAYhC0EKgv0L6CoJy5ZXsfr2JZ64aNApRWliJ4tx3kjTLP2Yjug_fd1tSBVvXCayzMz0swB2fXBIyHHFOaUAju9e9yke3xZYs5z2sg5lcCB75AZBaFqQelil8wAGK0VgNgnByk9AQBtWvmJ7DPO1QIUm5HLh2icN50bXd5UYaguXUpubbJ7weoOo8V1jsHX5yZhX_2cjM_TqrrFKZqxSH4N8Xc6InuDGRN-ftND8uvq28PFTb38cf394mxZW8ZkrhE6urCmlcBsNwDvlAArTD9wUH3T9c0getYPAjjjindSIbMDCA6tLAHI2CH5ss0NKTudrMtoH23wHm3WVKmmWcgCnWyhdQzPE6asVy5ZHEfjMUxJN20rhGSCQUGP39CpW2Gv19GtTNzo93kK8HUL2BhSijjo0lm2CT6X2UZNQf99Q__zhi5v6O0bxd7-Z39v-MD4B_2VkgQ
CitedBy_id crossref_primary_10_1038_s41467_025_63099_6
crossref_primary_10_1088_1361_6633_ad82cf
crossref_primary_10_1103_PhysRevResearch_6_013076
crossref_primary_10_1088_2058_9565_ad152e
crossref_primary_10_3390_drones7070413
crossref_primary_10_1007_s42484_023_00132_1
crossref_primary_10_1038_s41534_024_00804_1
crossref_primary_10_1038_s42254_025_00813_9
crossref_primary_10_1103_PhysRevResearch_5_L032040
crossref_primary_10_1007_JHEP01_2023_090
crossref_primary_10_1088_1367_2630_aceff4
crossref_primary_10_3390_ma16124300
crossref_primary_10_1140_epjqt_s40507_025_00335_4
crossref_primary_10_1038_s41534_024_00902_0
crossref_primary_10_1103_PhysRevApplied_21_067001
crossref_primary_10_3233_JIFS_221017
crossref_primary_10_1088_2058_9565_aca55d
crossref_primary_10_1103_PRXQuantum_3_030341
crossref_primary_10_3390_electronics13204136
crossref_primary_10_1103_PhysRevA_111_052403
crossref_primary_10_3390_foundations5030023
crossref_primary_10_1038_s41467_024_49287_w
crossref_primary_10_1103_rbhx_3fjd
crossref_primary_10_1103_PhysRevResearch_7_023151
crossref_primary_10_1016_j_neunet_2024_106508
crossref_primary_10_1088_1361_6633_ad85f0
crossref_primary_10_1088_2058_9565_acb56a
crossref_primary_10_1038_s41467_022_32550_3
crossref_primary_10_1007_s11128_025_04881_9
crossref_primary_10_1007_s12190_024_02136_x
crossref_primary_10_1088_2058_9565_adf771
crossref_primary_10_1038_s43588_022_00311_3
crossref_primary_10_1016_j_physa_2023_129286
crossref_primary_10_1016_j_jii_2024_100663
crossref_primary_10_1103_PhysRevA_111_062405
crossref_primary_10_1103_PhysRevResearch_7_013177
crossref_primary_10_1140_epjp_s13360_023_04537_6
crossref_primary_10_1007_s00220_024_05217_x
crossref_primary_10_1088_2058_9565_acc4e3
crossref_primary_10_1088_2058_9565_acc4e4
crossref_primary_10_1038_s41534_022_00611_6
crossref_primary_10_1103_PhysRevA_111_012441
crossref_primary_10_1103_PhysRevResearch_6_043028
crossref_primary_10_1103_PhysRevA_111_032403
crossref_primary_10_1007_s42484_025_00239_7
crossref_primary_10_1103_PhysRevApplied_22_054005
crossref_primary_10_1103_PhysRevResearch_6_023181
crossref_primary_10_1088_2632_2153_acff39
crossref_primary_10_1103_PhysRevLett_129_190501
crossref_primary_10_1109_COMST_2024_3399612
crossref_primary_10_1103_PhysRevResearch_6_023020
crossref_primary_10_1016_j_physa_2024_129690
crossref_primary_10_1103_PRXQuantum_4_040335
crossref_primary_10_1007_s11128_023_03881_x
crossref_primary_10_1016_j_neunet_2025_107442
crossref_primary_10_1038_s41467_024_49909_3
crossref_primary_10_1103_PRXQuantum_5_020328
crossref_primary_10_1103_PhysRevA_106_062434
crossref_primary_10_1103_PRXQuantum_6_010317
crossref_primary_10_1007_s42484_023_00103_6
crossref_primary_10_1103_PhysRevResearch_6_013241
crossref_primary_10_1088_2058_9565_acef55
crossref_primary_10_3390_e27070733
crossref_primary_10_22331_q_2025_08_29_1841
crossref_primary_10_1002_qute_202400074
crossref_primary_10_1007_s42484_024_00222_8
crossref_primary_10_1088_2632_2153_acb12f
crossref_primary_10_3389_fphy_2024_1412664
crossref_primary_10_1088_2058_9565_ad0a05
crossref_primary_10_1103_PRXQuantum_5_037001
crossref_primary_10_1038_s41467_024_45882_z
crossref_primary_10_1088_1361_6633_ad7f69
Cites_doi 10.1103/PhysRevX.11.041011
10.1038/s41467-021-21728-w
10.1103/PhysRevResearch.1.033063
10.1038/323533a0
10.1038/ncomms5213
10.1088/2058-9565/aa8072
10.1038/s41567-019-0648-8
10.1038/nature23879
10.1103/PhysRevResearch.3.033090
10.22331/q-2018-08-06-79
10.1038/s41467-019-11417-0
10.1103/PRXQuantum.2.040316
10.1007/s00521-004-0446-8
10.1103/PhysRevA.98.032309
10.1088/2058-9565/abd891
10.1088/1751-8121/ab434b
10.1103/PhysRevLett.128.070501
10.1007/s11128-013-0723-5
10.1103/PhysRevLett.124.130502
10.22331/q-2019-10-07-191
10.1088/1361-6633/aab406
10.7551/mitpress/11301.001.0001
10.1038/s41534-019-0167-6
10.22331/q-2019-12-09-214
10.1515/bpasts-2017-0003
10.1088/1367-2630/ab784c
10.1098/rspa.2017.0551
10.1038/s41467-020-14454-2
10.1007/s00220-016-2706-8
10.1016/j.scib.2021.06.023
10.1038/s41467-018-07090-4
10.1007/s11128-014-0809-8
10.1038/s41467-021-27045-6
10.1038/s41534-019-0140-4
10.1103/PhysRevA.80.012304
10.1038/s41567-020-0932-7
10.1103/PhysRevA.99.062304
10.1002/qute.201800077
10.22331/q-2021-06-04-466
10.1038/s43588-021-00084-1
10.22331/q-2020-03-26-248
10.1103/PhysRevLett.127.110502
10.1103/PhysRevA.99.032331
10.1103/PhysRevX.6.031045
10.1088/1367-2630/18/2/023023
10.1038/nature23474
10.22331/q-2020-05-25-269
10.1103/PhysRevResearch.2.033125
10.1038/s41534-020-00302-0
10.22331/q-2019-05-13-140
10.1038/s41586-019-0980-2
10.22331/q-2020-05-11-263
10.1209/0295-5075/125/30004
ContentType Journal Article
CorporateAuthor Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
CorporateAuthor_xml – name: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
DBID AAYXX
CITATION
NPM
7X8
OIOZB
OTOTI
DOI 10.1103/PhysRevLett.128.180505
DatabaseName CrossRef
PubMed
MEDLINE - Academic
OSTI.GOV - Hybrid
OSTI.GOV
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList PubMed

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 1079-7114
ExternalDocumentID 1992248
35594093
10_1103_PhysRevLett_128_180505
Genre Journal Article
GroupedDBID ---
-DZ
-~X
123
186
2-P
29O
3MX
3O-
41~
5VS
6TJ
85S
8NH
8WZ
9M8
A6W
AAYJJ
AAYXX
ABSSX
ABUFD
ACBEA
ACGFO
ACKIV
ACNCT
ADXHL
AECSF
AENEX
AEQTI
AETEA
AFFNX
AFGMR
AGDNE
AJQPL
ALMA_UNASSIGNED_HOLDINGS
APKKM
AUAIK
CITATION
CS3
D0L
DU5
EBS
EJD
ER.
F5P
H~9
MVM
N9A
NEJ
NHB
NPBMV
OHT
OK1
P0-
P2P
RNS
ROL
S7W
SJN
T9H
TN5
UBC
UBE
VOH
WH7
XOL
XSW
YNT
YYP
ZCG
ZPR
ZY4
~02
NPM
UCJ
VQA
7X8
60C
ABCKA
ADETJ
OIOZB
OTOTI
XFK
ID FETCH-LOGICAL-c338t-e0b14ca6803cbf05b970c7adf509d2bd2f7d3df7053595b89e3cf075068c33e33
IEDL.DBID 3MX
ISICitedReferencesCount 97
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000806849800006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-9007
1079-7114
IngestDate Mon Feb 12 04:54:57 EST 2024
Thu Jul 10 22:01:41 EDT 2025
Wed Feb 19 02:24:23 EST 2025
Sat Nov 29 07:42:16 EST 2025
Tue Nov 18 22:00:04 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 18
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c338t-e0b14ca6803cbf05b970c7adf509d2bd2f7d3df7053595b89e3cf075068c33e33
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
89233218CNA000001
LA-UR-20-23484
USDOE Laboratory Directed Research and Development (LDRD) Program
ORCID 0000-0002-6758-4376
0000-0002-2757-3170
0000-0003-3132-1088
0000000227573170
0000000198798425
0000000267584376
0000000331321088
OpenAccessLink https://www.osti.gov/servlets/purl/1992248
PMID 35594093
PQID 2667783730
PQPubID 23479
ParticipantIDs osti_scitechconnect_1992248
proquest_miscellaneous_2667783730
pubmed_primary_35594093
crossref_citationtrail_10_1103_PhysRevLett_128_180505
crossref_primary_10_1103_PhysRevLett_128_180505
PublicationCentury 2000
PublicationDate 2022-05-06
PublicationDateYYYYMMDD 2022-05-06
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-05-06
  day: 06
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Physical review letters
PublicationTitleAlternate Phys Rev Lett
PublicationYear 2022
Publisher American Physical Society (APS)
Publisher_xml – name: American Physical Society (APS)
References PhysRevLett.128.180505Cc31R1
PhysRevLett.128.180505Cc52R1
PhysRevLett.128.180505Cc54R1
PhysRevLett.128.180505Cc35R1
PhysRevLett.128.180505Cc37R1
PhysRevLett.128.180505Cc58R1
PhysRevLett.128.180505Cc9R1
PhysRevLett.128.180505Cc14R1
PhysRevLett.128.180505Cc5R1
PhysRevLett.128.180505Cc10R1
PhysRevLett.128.180505Cc50R1
PhysRevLett.128.180505Cc71R1
Simon Haykin (PhysRevLett.128.180505Cc1R1) 1994
PhysRevLett.128.180505Cc18R1
PhysRevLett.128.180505Cc16R1
PhysRevLett.128.180505Cc42R1
Marvin Minsky (PhysRevLett.128.180505Cc2R1) 2017
PhysRevLett.128.180505Cc44R1
PhysRevLett.128.180505Cc65R1
PhysRevLett.128.180505Cc46R1
PhysRevLett.128.180505Cc69R1
PhysRevLett.128.180505Cc25R1
PhysRevLett.128.180505Cc23R1
PhysRevLett.128.180505Cc21R1
PhysRevLett.128.180505Cc61R1
PhysRevLett.128.180505Cc29R1
PhysRevLett.128.180505Cc27R1
PhysRevLett.128.180505Cc55R1
PhysRevLett.128.180505Cc4R1
PhysRevLett.128.180505Cc34R1
PhysRevLett.128.180505Cc57R1
PhysRevLett.128.180505Cc36R1
PhysRevLett.128.180505Cc15R1
Neena Aloysius (PhysRevLett.128.180505Cc56R1) 2017
PhysRevLett.128.180505Cc11R1
PhysRevLett.128.180505Cc6R1
PhysRevLett.128.180505Cc70R1
PhysRevLett.128.180505Cc51R1
PhysRevLett.128.180505Cc8R1
PhysRevLett.128.180505Cc19R1
PhysRevLett.128.180505Cc17R1
PhysRevLett.128.180505Cc38R1
Frank Rosenblatt (PhysRevLett.128.180505Cc3R1) 1957
PhysRevLett.128.180505Cc41R1
PhysRevLett.128.180505Cc64R1
PhysRevLett.128.180505Cc43R1
PhysRevLett.128.180505Cc66R1
PhysRevLett.128.180505Cc45R1
PhysRevLett.128.180505Cc68R1
PhysRevLett.128.180505Cc47R1
PhysRevLett.128.180505Cc24R1
PhysRevLett.128.180505Cc22R1
PhysRevLett.128.180505Cc20R1
PhysRevLett.128.180505Cc62R1
PhysRevLett.128.180505Cc28R1
PhysRevLett.128.180505Cc49R1
Michael A. Nielsen (PhysRevLett.128.180505Cc7R1) 2015
References_xml – volume-title: Neural Networks: A Comprehensive Foundation
  year: 1994
  ident: PhysRevLett.128.180505Cc1R1
– ident: PhysRevLett.128.180505Cc66R1
  doi: 10.1103/PhysRevX.11.041011
– ident: PhysRevLett.128.180505Cc19R1
  doi: 10.1038/s41467-021-21728-w
– ident: PhysRevLett.128.180505Cc15R1
  doi: 10.1103/PhysRevResearch.1.033063
– ident: PhysRevLett.128.180505Cc4R1
  doi: 10.1038/323533a0
– ident: PhysRevLett.128.180505Cc20R1
  doi: 10.1038/ncomms5213
– ident: PhysRevLett.128.180505Cc10R1
  doi: 10.1088/2058-9565/aa8072
– ident: PhysRevLett.128.180505Cc16R1
  doi: 10.1038/s41567-019-0648-8
– ident: PhysRevLett.128.180505Cc54R1
  doi: 10.1038/nature23879
– ident: PhysRevLett.128.180505Cc71R1
  doi: 10.1103/PhysRevResearch.3.033090
– ident: PhysRevLett.128.180505Cc5R1
  doi: 10.22331/q-2018-08-06-79
– ident: PhysRevLett.128.180505Cc23R1
  doi: 10.1038/s41467-019-11417-0
– ident: PhysRevLett.128.180505Cc55R1
  doi: 10.1103/PRXQuantum.2.040316
– ident: PhysRevLett.128.180505Cc31R1
  doi: 10.1007/s00521-004-0446-8
– ident: PhysRevLett.128.180505Cc49R1
  doi: 10.1103/PhysRevA.98.032309
– ident: PhysRevLett.128.180505Cc64R1
  doi: 10.1088/2058-9565/abd891
– ident: PhysRevLett.128.180505Cc42R1
  doi: 10.1088/1751-8121/ab434b
– ident: PhysRevLett.128.180505Cc9R1
  doi: 10.1103/PhysRevLett.128.070501
– ident: PhysRevLett.128.180505Cc34R1
  doi: 10.1007/s11128-013-0723-5
– ident: PhysRevLett.128.180505Cc38R1
  doi: 10.1103/PhysRevLett.124.130502
– ident: PhysRevLett.128.180505Cc27R1
  doi: 10.22331/q-2019-10-07-191
– ident: PhysRevLett.128.180505Cc11R1
  doi: 10.1088/1361-6633/aab406
– volume-title: Perceptrons: An Introduction to Computational Geometry
  year: 2017
  ident: PhysRevLett.128.180505Cc2R1
  doi: 10.7551/mitpress/11301.001.0001
– ident: PhysRevLett.128.180505Cc61R1
  doi: 10.1038/s41534-019-0167-6
– ident: PhysRevLett.128.180505Cc62R1
  doi: 10.22331/q-2019-12-09-214
– ident: PhysRevLett.128.180505Cc41R1
  doi: 10.1515/bpasts-2017-0003
– volume-title: The Perceptron, a Perceiving and Recognizing Automaton Project Para
  year: 1957
  ident: PhysRevLett.128.180505Cc3R1
– ident: PhysRevLett.128.180505Cc44R1
  doi: 10.1088/1367-2630/ab784c
– ident: PhysRevLett.128.180505Cc14R1
  doi: 10.1098/rspa.2017.0551
– ident: PhysRevLett.128.180505Cc37R1
  doi: 10.1038/s41467-020-14454-2
– ident: PhysRevLett.128.180505Cc52R1
  doi: 10.1007/s00220-016-2706-8
– ident: PhysRevLett.128.180505Cc25R1
  doi: 10.1016/j.scib.2021.06.023
– ident: PhysRevLett.128.180505Cc18R1
  doi: 10.1038/s41467-018-07090-4
– ident: PhysRevLett.128.180505Cc6R1
  doi: 10.1007/s11128-014-0809-8
– ident: PhysRevLett.128.180505Cc69R1
  doi: 10.1038/s41467-021-27045-6
– ident: PhysRevLett.128.180505Cc36R1
  doi: 10.1038/s41534-019-0140-4
– ident: PhysRevLett.128.180505Cc51R1
  doi: 10.1103/PhysRevA.80.012304
– ident: PhysRevLett.128.180505Cc45R1
  doi: 10.1038/s41567-020-0932-7
– ident: PhysRevLett.128.180505Cc24R1
  doi: 10.1103/PhysRevA.99.062304
– ident: PhysRevLett.128.180505Cc17R1
  doi: 10.1002/qute.201800077
– ident: PhysRevLett.128.180505Cc68R1
  doi: 10.22331/q-2021-06-04-466
– ident: PhysRevLett.128.180505Cc70R1
  doi: 10.1038/s43588-021-00084-1
– ident: PhysRevLett.128.180505Cc29R1
  doi: 10.22331/q-2020-03-26-248
– ident: PhysRevLett.128.180505Cc65R1
  doi: 10.1103/PhysRevLett.127.110502
– ident: PhysRevLett.128.180505Cc50R1
  doi: 10.1103/PhysRevA.99.032331
– ident: PhysRevLett.128.180505Cc21R1
  doi: 10.1103/PhysRevX.6.031045
– ident: PhysRevLett.128.180505Cc22R1
  doi: 10.1088/1367-2630/18/2/023023
– ident: PhysRevLett.128.180505Cc8R1
  doi: 10.1038/nature23474
– ident: PhysRevLett.128.180505Cc57R1
  doi: 10.22331/q-2020-05-25-269
– ident: PhysRevLett.128.180505Cc47R1
  doi: 10.1103/PhysRevResearch.2.033125
– ident: PhysRevLett.128.180505Cc28R1
  doi: 10.1038/s41534-020-00302-0
– ident: PhysRevLett.128.180505Cc46R1
  doi: 10.22331/q-2019-05-13-140
– ident: PhysRevLett.128.180505Cc43R1
  doi: 10.1038/s41586-019-0980-2
– ident: PhysRevLett.128.180505Cc58R1
  doi: 10.22331/q-2020-05-11-263
– volume-title: Neural Networks and Deep Learning
  year: 2015
  ident: PhysRevLett.128.180505Cc7R1
– volume-title: 2017 International Conference on Communication and Signal Processing (ICCSP)
  year: 2017
  ident: PhysRevLett.128.180505Cc56R1
– ident: PhysRevLett.128.180505Cc35R1
  doi: 10.1209/0295-5075/125/30004
SSID ssj0001268
Score 2.6977098
Snippet Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data....
SourceID osti
proquest
pubmed
crossref
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 180505
SubjectTerms artificial neural networks
CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS
machine learning
quantum algorithms
quantum computation
quantum information processing
quantum networks
Title Trainability of Dissipative Perceptron-Based Quantum Neural Networks
URI https://www.ncbi.nlm.nih.gov/pubmed/35594093
https://www.proquest.com/docview/2667783730
https://www.osti.gov/servlets/purl/1992248
Volume 128
WOSCitedRecordID wos000806849800006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVABR
  databaseName: American Physical Society Journals
  customDbUrl:
  eissn: 1079-7114
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001268
  issn: 0031-9007
  databaseCode: 3MX
  dateStart: 20020101
  isFulltext: true
  titleUrlDefault: https://journals.aps.org/
  providerName: American Physical Society
– providerCode: PRVIAO
  databaseName: SCOAP3 Journals
  customDbUrl:
  eissn: 1079-7114
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001268
  issn: 0031-9007
  databaseCode: ER.
  dateStart: 20180101
  isFulltext: true
  titleUrlDefault: https://scoap3.org/
  providerName: SCOAP3 (Sponsoring Consortium for Open Access Publishing in Particle Physics)
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5KUfDi-1GrEsFr2k02ye4e1Vq8WKpU6C0kuxsQNJH0Af57Z5K2KFikl5ySyTK7O_sN-803ADeJ8RGE2tBNRCrdwNoI95xUCOSSyEbKeFwkVbMJMRjI8VgNG8D-vsH3GO8SE_LFzqm6pYPBtONJar5GQVcG1LKAP41Xodfzozr0cuIdMLEoCV5v5tdp1CxwV61HmtWJ09_bfKz7sLtAl85tvRwOoGHzQ9iuWJ56cgS9UVkVSxEf9sspMqeHbq841XPrDGuKS1nk7h0ebcZ5nqHXZx8O6Xeg0UFNGJ8cw2v_YXT_6C7aKLga88-pa1nqBTqJJOM6zViYKsG0SEyGWMH4qfEzYbjJBCm9qDCVynKdEZKIJBqwnJ9AMy9yewaODWygWMqUFjzgIpNGeTyMJImeKbTUgnDpzlgvNMap1cV7XOUajMc_PBSjh-LaQy3orr77rFU2_v2iTbMVI04gsVtNrCCNL5DMbiBbcL2cxBi3C92BJLktZpMY8YgQmJRz1oLTenZXf0TopTDd5ecbj6YNOz6VRRARMrqA5rSc2UvY0vPp26S8qtYoPsVYfgOyGeQp
linkProvider American Physical Society
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Trainability+of+Dissipative+Perceptron-Based+Quantum+Neural+Networks&rft.jtitle=Physical+review+letters&rft.au=Sharma%2C+Kunal&rft.au=Cerezo%2C+M&rft.au=Cincio%2C+Lukasz&rft.au=Coles%2C+Patrick+J&rft.date=2022-05-06&rft.issn=1079-7114&rft.eissn=1079-7114&rft.volume=128&rft.issue=18&rft.spage=180505&rft_id=info:doi/10.1103%2FPhysRevLett.128.180505&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-9007&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-9007&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-9007&client=summon