There have been numerous quantum neural networks reported, but they struggle to match traditional neural networks in accuracy. Given the huge improvement of the neural network models’ accuracy by two-dimensional tensor network states in classical tensor network machine learning, it is promising to explore whether its application in quantum machine learning can extend the performance boundary of the models. Here, we transform two-dimensional tensor networks into quantum circuits for supervised learning. Specifically, we encode two-dimensional tensor networks into quantum circuits through rigorous mathematical proofs for constructing model ansätze, including string-bond states, entangled-plaquette states and isometric tensor network states. In addition, we propose adaptive data encoding methods and combine with tensor networks. We construct a tensor-network-inspired quantum circuit supervised learning framework for transferring tensor network machine learning from classical to quantum, and build several novel two-dimensional tensor network-inspired quantum classifiers based on this framework. Finally, we propose a parallel quantum machine learning method for multi-class classification to construct 2D TNQC-based multi-class classifiers. Classical simulation results on the MNIST benchmark dataset show that our proposed models achieve the state-of-the-art accuracy performance, significantly outperforming other quantum classifiers on both binary and multi-class classification tasks, and beat simple convolutional classifiers on a fair track with identical inputs. The noise resilience of the models makes them successfully run and work in a real quantum computer.
{"title":"Transforming two-dimensional tensor networks into quantum circuits for supervised learning","authors":"Zhihui Song, Jinchen Xu, Xin Zhou, X. Ding, Zheng Shan","doi":"10.1088/2632-2153/ad2fec","DOIUrl":"https://doi.org/10.1088/2632-2153/ad2fec","url":null,"abstract":"\u0000 There have been numerous quantum neural networks reported, but they struggle to match traditional neural networks in accuracy. Given the huge improvement of the neural network models’ accuracy by two-dimensional tensor network states in classical tensor network machine learning, it is promising to explore whether its application in quantum machine learning can extend the performance boundary of the models. Here, we transform two-dimensional tensor networks into quantum circuits for supervised learning. Specifically, we encode two-dimensional tensor networks into quantum circuits through rigorous mathematical proofs for constructing model ansätze, including string-bond states, entangled-plaquette states and isometric tensor network states. In addition, we propose adaptive data encoding methods and combine with tensor networks. We construct a tensor-network-inspired quantum circuit supervised learning framework for transferring tensor network machine learning from classical to quantum, and build several novel two-dimensional tensor network-inspired quantum classifiers based on this framework. Finally, we propose a parallel quantum machine learning method for multi-class classification to construct 2D TNQC-based multi-class classifiers. Classical simulation results on the MNIST benchmark dataset show that our proposed models achieve the state-of-the-art accuracy performance, significantly outperforming other quantum classifiers on both binary and multi-class classification tasks, and beat simple convolutional classifiers on a fair track with identical inputs. The noise resilience of the models makes them successfully run and work in a real quantum computer.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"23 8","pages":"15048"},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140265831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-26DOI: 10.1088/2632-2153/ABFBBA
N. Creange, K. P. Kelley, C. Smith, D. Sando, O. Paull, N. Valanoor, S. Somnath, S. Jesse, S. Kalinin, R. Vasudevan
{"title":"Propagation of priors for more accurate and efficient spectroscopic functional fits and their application to ferroelectric hysteresis","authors":"N. Creange, K. P. Kelley, C. Smith, D. Sando, O. Paull, N. Valanoor, S. Somnath, S. Jesse, S. Kalinin, R. Vasudevan","doi":"10.1088/2632-2153/ABFBBA","DOIUrl":"https://doi.org/10.1088/2632-2153/ABFBBA","url":null,"abstract":"","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"36 1","pages":"45002"},"PeriodicalIF":0.0,"publicationDate":"2021-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75005950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-20DOI: 10.1088/2632-2153/ABF9B1
Alessandro Greco, V. Starostin, A. Hinderhofer, A. Gerlach, M. Skoda, S. Kowarik, F. Schreiber
{"title":"Neural network analysis of neutron and x-ray reflectivity data: pathological cases, performance and perspectives","authors":"Alessandro Greco, V. Starostin, A. Hinderhofer, A. Gerlach, M. Skoda, S. Kowarik, F. Schreiber","doi":"10.1088/2632-2153/ABF9B1","DOIUrl":"https://doi.org/10.1088/2632-2153/ABF9B1","url":null,"abstract":"","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"5 1","pages":"45003"},"PeriodicalIF":0.0,"publicationDate":"2021-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81965773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-13DOI: 10.1088/2632-2153/ABF751
Gilchan Park, Line C. Pouchard
{"title":"Advances in scientific literature mining for interpreting materials characterization","authors":"Gilchan Park, Line C. Pouchard","doi":"10.1088/2632-2153/ABF751","DOIUrl":"https://doi.org/10.1088/2632-2153/ABF751","url":null,"abstract":"","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"57 1","pages":"45007"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72777738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-07DOI: 10.1088/2632-2153/ABF5B9
Yu Feng, Y. Tu
{"title":"Phases of learning dynamics in artificial neural networks in the absence or presence of mislabeled data","authors":"Yu Feng, Y. Tu","doi":"10.1088/2632-2153/ABF5B9","DOIUrl":"https://doi.org/10.1088/2632-2153/ABF5B9","url":null,"abstract":"","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"8 1","pages":"43001"},"PeriodicalIF":0.0,"publicationDate":"2021-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78961160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-07DOI: 10.1088/2632-2153/ABF5B7
Daniel Flam-Shepherd, Tony C Wu, Alán Aspuru-Guzik
{"title":"MPGVAE: improved generation of small organic molecules using message passing neural nets","authors":"Daniel Flam-Shepherd, Tony C Wu, Alán Aspuru-Guzik","doi":"10.1088/2632-2153/ABF5B7","DOIUrl":"https://doi.org/10.1088/2632-2153/ABF5B7","url":null,"abstract":"","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"51 1","pages":"45010"},"PeriodicalIF":0.0,"publicationDate":"2021-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85864909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-25DOI: 10.1088/2632-2153/ABF22C
A. Halder, B. Datta
Since the onset of 2020, the spread of coronavirus disease (COVID-19) has rapidly accelerated worldwide into a state of severe pandemic. COVID-19 has infected more than 29 million people and caused more than 900 thousand deaths at the time of writing. Since it is highly contagious, it causes explosive community transmission. Thus, health care delivery has been disrupted and compromised by the lack of testing kits. COVID-19-infected patients show severe acute respiratory syndrome. Meanwhile, the scientific community has been involved in the implementation of deep learning (DL) techniques to diagnose COVID-19 using computed tomography (CT) lung scans, since CT is a pertinent screening tool due to its higher sensitivity in recognizing early pneumonic changes. However, large datasets of CT-scan images are not publicly available due to privacy concerns and obtaining very accurate models has become difficult. Thus, to overcome this drawback, transfer-learning pre-trained models are used in the proposed methodology to classify COVID-19 (positive) and COVID-19 (negative) patients. We describe the development of a DL framework that includes pre-trained models (DenseNet201, VGG16, ResNet50V2, and MobileNet) as its backbone, known as KarNet. To extensively test and analyze the framework, each model was trained on original (i.e. unaugmented) and manipulated (i.e. augmented) datasets. Among the four pre-trained models of KarNet, the one that used DenseNet201 demonstrated excellent diagnostic ability, with AUC scores of 1.00 and 0.99 for models trained on unaugmented and augmented data sets, respectively. Even after considerable distortion of the images (i.e. the augmented dataset) DenseNet201 achieved an accuracy of 97% for the test dataset, followed by ResNet50V2, MobileNet, and VGG16 (which achieved accuracies of 96%, 95%, and 94%, respectively).
{"title":"COVID-19 detection from lung CT-scan images using transfer learning approach","authors":"A. Halder, B. Datta","doi":"10.1088/2632-2153/ABF22C","DOIUrl":"https://doi.org/10.1088/2632-2153/ABF22C","url":null,"abstract":"Since the onset of 2020, the spread of coronavirus disease (COVID-19) has rapidly accelerated worldwide into a state of severe pandemic. COVID-19 has infected more than 29 million people and caused more than 900 thousand deaths at the time of writing. Since it is highly contagious, it causes explosive community transmission. Thus, health care delivery has been disrupted and compromised by the lack of testing kits. COVID-19-infected patients show severe acute respiratory syndrome. Meanwhile, the scientific community has been involved in the implementation of deep learning (DL) techniques to diagnose COVID-19 using computed tomography (CT) lung scans, since CT is a pertinent screening tool due to its higher sensitivity in recognizing early pneumonic changes. However, large datasets of CT-scan images are not publicly available due to privacy concerns and obtaining very accurate models has become difficult. Thus, to overcome this drawback, transfer-learning pre-trained models are used in the proposed methodology to classify COVID-19 (positive) and COVID-19 (negative) patients. We describe the development of a DL framework that includes pre-trained models (DenseNet201, VGG16, ResNet50V2, and MobileNet) as its backbone, known as KarNet. To extensively test and analyze the framework, each model was trained on original (i.e. unaugmented) and manipulated (i.e. augmented) datasets. Among the four pre-trained models of KarNet, the one that used DenseNet201 demonstrated excellent diagnostic ability, with AUC scores of 1.00 and 0.99 for models trained on unaugmented and augmented data sets, respectively. Even after considerable distortion of the images (i.e. the augmented dataset) DenseNet201 achieved an accuracy of 97% for the test dataset, followed by ResNet50V2, MobileNet, and VGG16 (which achieved accuracies of 96%, 95%, and 94%, respectively).","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"18 1","pages":"45013"},"PeriodicalIF":0.0,"publicationDate":"2021-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76476231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-15DOI: 10.1088/2632-2153/ac0123
L. Knijff, Chao Zhang
Molecular dipole moment in liquid water is an intriguing property, partly due to the fact that there is no unique way to partition the total electron density into individual molecular contributions. The prevailing method to circumvent this problem is to use maximally localized Wannier functions, which perform a unitary transformation of the occupied molecular orbitals by minimizing the spread function of Boys. Here we revisit this problem using a data-driven approach satisfying two physical constraints, namely: i) The displacement of the atomic charges is proportional to the Berry phase polarization; ii) Each water molecule has a formal charge of zero. It turns out that the distribution of molecular dipole moments in liquid water inferred from latent variables is surprisingly similar to that obtained from maximally localized Wannier functions. Apart from putting a maximum-likelihood footnote to the established method, this work highlights the capability of graph convolution based charge models and the importance of physical constraints on improving the interpretability.
{"title":"Machine learning inference of molecular dipole moment in liquid water","authors":"L. Knijff, Chao Zhang","doi":"10.1088/2632-2153/ac0123","DOIUrl":"https://doi.org/10.1088/2632-2153/ac0123","url":null,"abstract":"Molecular dipole moment in liquid water is an intriguing property, partly due to the fact that there is no unique way to partition the total electron density into individual molecular contributions. The prevailing method to circumvent this problem is to use maximally localized Wannier functions, which perform a unitary transformation of the occupied molecular orbitals by minimizing the spread function of Boys. Here we revisit this problem using a data-driven approach satisfying two physical constraints, namely: i) The displacement of the atomic charges is proportional to the Berry phase polarization; ii) Each water molecule has a formal charge of zero. It turns out that the distribution of molecular dipole moments in liquid water inferred from latent variables is surprisingly similar to that obtained from maximally localized Wannier functions. Apart from putting a maximum-likelihood footnote to the established method, this work highlights the capability of graph convolution based charge models and the importance of physical constraints on improving the interpretability.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"9 1","pages":"03"},"PeriodicalIF":0.0,"publicationDate":"2021-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81304817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-13DOI: 10.1088/2632-2153/abf3d0
F. Morawski, M. Bejger, E. Cuoco, Luigia Petre
As of this moment, fifty gravitational waves (GW) detections have been announced, thanks to the observational efforts of the LIGO-Virgo Collaboration, working with the Advanced LIGO and the Advanced Virgo interferometers. The detection of signals is complicated by the noise-dominated nature of the data. Conventional approaches in GW detection procedures require either precise knowledge of the GW waveform in the context of matched filtering searches or coincident analysis of data from multiple detectors. Furthermore, the analysis is prone to contamination by instrumental or environmental artifacts called glitches which either mimic astrophysical signals or reduce the overall quality of data. In this paper, we propose an alternative generic method of studying GW data based on detecting anomalies. The anomalies we study are transient signals, different from the slow non-stationary noise of the detector. Presented in the manuscript anomalies are mostly based on the GW emitted by the mergers of binary black hole systems. However, the presented study of anomalies is not limited only to GW alone, but also includes glitches occurring in the real LIGO/Virgo dataset available at the Gravitational Waves Open Science Center.
{"title":"Anomaly detection in gravitational waves data using convolutional autoencoders","authors":"F. Morawski, M. Bejger, E. Cuoco, Luigia Petre","doi":"10.1088/2632-2153/abf3d0","DOIUrl":"https://doi.org/10.1088/2632-2153/abf3d0","url":null,"abstract":"As of this moment, fifty gravitational waves (GW) detections have been announced, thanks to the observational efforts of the LIGO-Virgo Collaboration, working with the Advanced LIGO and the Advanced Virgo interferometers. The detection of signals is complicated by the noise-dominated nature of the data. Conventional approaches in GW detection procedures require either precise knowledge of the GW waveform in the context of matched filtering searches or coincident analysis of data from multiple detectors. Furthermore, the analysis is prone to contamination by instrumental or environmental artifacts called glitches which either mimic astrophysical signals or reduce the overall quality of data. In this paper, we propose an alternative generic method of studying GW data based on detecting anomalies. The anomalies we study are transient signals, different from the slow non-stationary noise of the detector. Presented in the manuscript anomalies are mostly based on the GW emitted by the mergers of binary black hole systems. However, the presented study of anomalies is not limited only to GW alone, but also includes glitches occurring in the real LIGO/Virgo dataset available at the Gravitational Waves Open Science Center.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"10 1","pages":"45014"},"PeriodicalIF":0.0,"publicationDate":"2021-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90176678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：