Pub Date : 2021-01-01DOI: 10.1088/2632-2153/ac0167
Tommy Liu, A. Barnard
{"title":"Fast derivation of Shapley based feature importances through feature extraction methods for nanoinformatics","authors":"Tommy Liu, A. Barnard","doi":"10.1088/2632-2153/ac0167","DOIUrl":"https://doi.org/10.1088/2632-2153/ac0167","url":null,"abstract":"","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"12 1","pages":"35034"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76852325","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 : 2020-12-31DOI: 10.1088/2632-2153/abffe9
Prakriti Kayastha, R. Ramakrishnan
A cornerstone of materials science is Landau’s theory of continuous phase transitions. Crystal structures connected by Landau-type transitions are mathematically related through groupsubgroup relationships. In this study, we introduce “group-subgroup learning” and show including small unit cell phases of materials in the training set to decrease out-of-sample errors for modeling larger phases. The proposed approach is generic and is independent of the ML formalism, descriptors, or datasets; and extendable to other symmetry abstractions such as spin-, valency-, or charge order. Since available materials datasets are heterogeneous with too few examples for realizing the group-subgroup structure, we present the “FriezeRMQ1D” dataset of 8393 Q1D organometallic materials uniformly distributed across seven frieze groups and provide a proof-of-the-concept. For these materials, we report < 3% error with 25% training with the Faber–Christensen–Huang–Lilienfeld descriptor and compare its performance with a fingerprint representation that encodes materials composition as well as crystallographic Wyckoff positions.
{"title":"Machine learning modeling of materials with a group-subgroup structure","authors":"Prakriti Kayastha, R. Ramakrishnan","doi":"10.1088/2632-2153/abffe9","DOIUrl":"https://doi.org/10.1088/2632-2153/abffe9","url":null,"abstract":"A cornerstone of materials science is Landau’s theory of continuous phase transitions. Crystal structures connected by Landau-type transitions are mathematically related through groupsubgroup relationships. In this study, we introduce “group-subgroup learning” and show including small unit cell phases of materials in the training set to decrease out-of-sample errors for modeling larger phases. The proposed approach is generic and is independent of the ML formalism, descriptors, or datasets; and extendable to other symmetry abstractions such as spin-, valency-, or charge order. Since available materials datasets are heterogeneous with too few examples for realizing the group-subgroup structure, we present the “FriezeRMQ1D” dataset of 8393 Q1D organometallic materials uniformly distributed across seven frieze groups and provide a proof-of-the-concept. For these materials, we report < 3% error with 25% training with the Faber–Christensen–Huang–Lilienfeld descriptor and compare its performance with a fingerprint representation that encodes materials composition as well as crystallographic Wyckoff positions.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"6 1","pages":"35035"},"PeriodicalIF":0.0,"publicationDate":"2020-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84283094","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 : 2020-12-21DOI: 10.1088/2632-2153/abf834
Aidan Kehoe, P. Wittek, Yanbo Xue, Alejandro Pozas-Kerstjens
We provide a robust defence to adversarial attacks on discriminative algorithms. Neural networks are naturally vulnerable to small, tailored perturbations in the input data that lead to wrong predictions. On the contrary, generative models attempt to learn the distribution underlying a dataset, making them inherently more robust to small perturbations. We use Boltzmann machines for discrimination purposes as attack-resistant classifiers, and compare them against standard state-of-the-art adversarial defences. We find improvements ranging from 5% to 72% against attacks with Boltzmann machines on the MNIST dataset. We furthermore complement the training with quantum-enhanced sampling from the D-Wave 2000Q annealer, finding results comparable with classical techniques and with marginal improvements in some cases. These results underline the relevance of probabilistic methods in constructing neural networks and demonstrate the power of quantum computers, even with limited hardware capabilities. This work is dedicated to the memory of Peter Wittek.
{"title":"Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines","authors":"Aidan Kehoe, P. Wittek, Yanbo Xue, Alejandro Pozas-Kerstjens","doi":"10.1088/2632-2153/abf834","DOIUrl":"https://doi.org/10.1088/2632-2153/abf834","url":null,"abstract":"We provide a robust defence to adversarial attacks on discriminative algorithms. Neural networks are naturally vulnerable to small, tailored perturbations in the input data that lead to wrong predictions. On the contrary, generative models attempt to learn the distribution underlying a dataset, making them inherently more robust to small perturbations. We use Boltzmann machines for discrimination purposes as attack-resistant classifiers, and compare them against standard state-of-the-art adversarial defences. We find improvements ranging from 5% to 72% against attacks with Boltzmann machines on the MNIST dataset. We furthermore complement the training with quantum-enhanced sampling from the D-Wave 2000Q annealer, finding results comparable with classical techniques and with marginal improvements in some cases. These results underline the relevance of probabilistic methods in constructing neural networks and demonstrate the power of quantum computers, even with limited hardware capabilities. This work is dedicated to the memory of Peter Wittek.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"13 1","pages":"45006"},"PeriodicalIF":0.0,"publicationDate":"2020-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73542041","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 : 2020-12-17DOI: 10.1088/2632-2153/ac09d6
Cynthia X Shen, M. Krenn, S. Eppel, Alán Aspuru-Guzik
Computer-based de-novo design of functional molecules is one of the most prominent challenges in cheminformatics today. As a result, generative and evolutionary inverse designs from the field of artificial intelligence have emerged at a rapid pace, with aims to optimize molecules for a particular chemical property. These models 'indirectly' explore the chemical space; by learning latent spaces, policies, distributions or by applying mutations on populations of molecules. However, the recent development of the SELFIES string representation of molecules, a surjective alternative to SMILES, have made possible other potential techniques. Based on SELFIES, we therefore propose PASITHEA, a direct gradient-based molecule optimization that applies inceptionism techniques from computer vision. PASITHEA exploits the use of gradients by directly reversing the learning process of a neural network, which is trained to predict real-valued chemical properties. Effectively, this forms an inverse regression model, which is capable of generating molecular variants optimized for a certain property. Although our results are preliminary, we observe a shift in distribution of a chosen property during inverse-training, a clear indication of PASITHEA's viability. A striking property of inceptionism is that we can directly probe the model's understanding of the chemical space it was trained on. We expect that extending PASITHEA to larger datasets, molecules and more complex properties will lead to advances in the design of new functional molecules as well as the interpretation and explanation of machine learning models.
{"title":"Deep Molecular Dreaming: Inverse machine learning for de-novo molecular design and interpretability with surjective representations","authors":"Cynthia X Shen, M. Krenn, S. Eppel, Alán Aspuru-Guzik","doi":"10.1088/2632-2153/ac09d6","DOIUrl":"https://doi.org/10.1088/2632-2153/ac09d6","url":null,"abstract":"Computer-based de-novo design of functional molecules is one of the most prominent challenges in cheminformatics today. As a result, generative and evolutionary inverse designs from the field of artificial intelligence have emerged at a rapid pace, with aims to optimize molecules for a particular chemical property. These models 'indirectly' explore the chemical space; by learning latent spaces, policies, distributions or by applying mutations on populations of molecules. However, the recent development of the SELFIES string representation of molecules, a surjective alternative to SMILES, have made possible other potential techniques. Based on SELFIES, we therefore propose PASITHEA, a direct gradient-based molecule optimization that applies inceptionism techniques from computer vision. PASITHEA exploits the use of gradients by directly reversing the learning process of a neural network, which is trained to predict real-valued chemical properties. Effectively, this forms an inverse regression model, which is capable of generating molecular variants optimized for a certain property. Although our results are preliminary, we observe a shift in distribution of a chosen property during inverse-training, a clear indication of PASITHEA's viability. A striking property of inceptionism is that we can directly probe the model's understanding of the chemical space it was trained on. We expect that extending PASITHEA to larger datasets, molecules and more complex properties will lead to advances in the design of new functional molecules as well as the interpretation and explanation of machine learning models.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"82 1","pages":"03"},"PeriodicalIF":0.0,"publicationDate":"2020-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74223411","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 : 2020-11-30DOI: 10.1088/2632-2153/ABF3AC
A. Anand, M. Degroote, Alán Aspuru-Guzik
Natural evolutionary strategies (NES) are a family of gradient-free black-box optimization algorithms. This study illustrates their use for the optimization of randomly-initialized parametrized quantum circuits (PQCs) in the region of vanishing gradients. We show that using the NES gradient estimator the exponential decrease in variance can be alleviated. We implement two specific approaches, the exponential and separable natural evolutionary strategies, for parameter optimization of PQCs and compare them against standard gradient descent. We apply them to two different problems of ground state energy estimation using variational quantum eigensolver (VQE) and state preparation with circuits of varying depth and length. We also introduce batch optimization for circuits with larger depth to extend the use of evolutionary strategies to a larger number of parameters. We achieve accuracy comparable to state-of-the-art optimization techniques in all the above cases with a lower number of circuit evaluations. Our empirical results indicate that one can use NES as a hybrid tool in tandem with other gradient-based methods for optimization of deep quantum circuits in regions with vanishing gradients.
{"title":"Natural Evolutionary Strategies for Variational Quantum Computation","authors":"A. Anand, M. Degroote, Alán Aspuru-Guzik","doi":"10.1088/2632-2153/ABF3AC","DOIUrl":"https://doi.org/10.1088/2632-2153/ABF3AC","url":null,"abstract":"Natural evolutionary strategies (NES) are a family of gradient-free black-box optimization algorithms. This study illustrates their use for the optimization of randomly-initialized parametrized quantum circuits (PQCs) in the region of vanishing gradients. We show that using the NES gradient estimator the exponential decrease in variance can be alleviated. We implement two specific approaches, the exponential and separable natural evolutionary strategies, for parameter optimization of PQCs and compare them against standard gradient descent. We apply them to two different problems of ground state energy estimation using variational quantum eigensolver (VQE) and state preparation with circuits of varying depth and length. We also introduce batch optimization for circuits with larger depth to extend the use of evolutionary strategies to a larger number of parameters. We achieve accuracy comparable to state-of-the-art optimization techniques in all the above cases with a lower number of circuit evaluations. Our empirical results indicate that one can use NES as a hybrid tool in tandem with other gradient-based methods for optimization of deep quantum circuits in regions with vanishing gradients.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"40 1","pages":"45012"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82655881","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 : 2020-11-30DOI: 10.1088/2632-2153/ac0314
Lingxiao Wang, Tian Xu, Till Hannes Stoecker, H. Stoecker, Yin Jiang, K. Zhou
As the COVID-19 pandemic continues to ravage the world, it is of critical significance to provide a timely risk prediction of the COVID-19 in multi-level. To implement it and evaluate the public health policies, we develop a framework with machine learning assisted to extract epidemic dynamics from the infection data, in which contains a county-level spatiotemporal epidemiological model that combines a spatial Cellular Automaton (CA) with a temporal Susceptible-Undiagnosed-Infected-Removed (SUIR) model. Compared with the existing time risk prediction models, the proposed CA-SUIR model shows the multi-level risk of the county to the government and coronavirus transmission patterns under different policies. This new toolbox is first utilized to the projection of the multi-level COVID-19 prevalence over 412 Landkreis (counties) in Germany, including t-day-ahead risk forecast and the risk assessment to the travel restriction policy. As a practical illustration, we predict the situation at Christmas where the worst fatalities are 34.5 thousand, effective policies could contain it to below 21 thousand. Such intervenable evaluation system could help decide on economic restarting and public health policies making in pandemic.
{"title":"Machine learning spatio-temporal epidemiological model to evaluate Germany-county-level COVID-19 risk","authors":"Lingxiao Wang, Tian Xu, Till Hannes Stoecker, H. Stoecker, Yin Jiang, K. Zhou","doi":"10.1088/2632-2153/ac0314","DOIUrl":"https://doi.org/10.1088/2632-2153/ac0314","url":null,"abstract":"As the COVID-19 pandemic continues to ravage the world, it is of critical significance to provide a timely risk prediction of the COVID-19 in multi-level. To implement it and evaluate the public health policies, we develop a framework with machine learning assisted to extract epidemic dynamics from the infection data, in which contains a county-level spatiotemporal epidemiological model that combines a spatial Cellular Automaton (CA) with a temporal Susceptible-Undiagnosed-Infected-Removed (SUIR) model. Compared with the existing time risk prediction models, the proposed CA-SUIR model shows the multi-level risk of the county to the government and coronavirus transmission patterns under different policies. This new toolbox is first utilized to the projection of the multi-level COVID-19 prevalence over 412 Landkreis (counties) in Germany, including t-day-ahead risk forecast and the risk assessment to the travel restriction policy. As a practical illustration, we predict the situation at Christmas where the worst fatalities are 34.5 thousand, effective policies could contain it to below 21 thousand. Such intervenable evaluation system could help decide on economic restarting and public health policies making in pandemic.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"25 1","pages":"35031"},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78326923","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 : 2020-11-20DOI: 10.1088/2632-2153/abf5ee
L. Hofer, Milan Krstaji'c, P'eter Juh'asz, A. L. Marchant, Robert P. Smith
We use a deep neural network to detect and place region-of-interest boxes around ultracold atom clouds in absorption and fluorescence images---with the ability to identify and bound multiple clouds within a single image. The neural network also outputs segmentation masks that identify the size, shape and orientation of each cloud from which we extract the clouds' Gaussian parameters. This allows 2D Gaussian fits to be reliably seeded thereby enabling fully automatic image processing.
{"title":"Atom cloud detection and segmentation using a deep neural network","authors":"L. Hofer, Milan Krstaji'c, P'eter Juh'asz, A. L. Marchant, Robert P. Smith","doi":"10.1088/2632-2153/abf5ee","DOIUrl":"https://doi.org/10.1088/2632-2153/abf5ee","url":null,"abstract":"We use a deep neural network to detect and place region-of-interest boxes around ultracold atom clouds in absorption and fluorescence images---with the ability to identify and bound multiple clouds within a single image. The neural network also outputs segmentation masks that identify the size, shape and orientation of each cloud from which we extract the clouds' Gaussian parameters. This allows 2D Gaussian fits to be reliably seeded thereby enabling fully automatic image processing.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"2 1","pages":"45008"},"PeriodicalIF":0.0,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72909554","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 : 2020-11-16DOI: 10.1088/2632-2153/ABF856
Ilia Igashov, Nikita Pavlichenko, S. Grudinin
Processing information on 3D objects requires methods stable to rigid-body transformations, in particular rotations, of the input data. In image processing tasks, convolutional neural networks achieve this property using rotation-equivariant operations. However, contrary to images, graphs generally have irregular topology. This makes it challenging to define a rotation-equivariant convolution operation on these structures. In this work, we propose Spherical Graph Convolutional Network (S-GCN) that processes 3D models of proteins represented as molecular graphs. In a protein molecule, individual amino acids have common topological elements. This allows us to unambiguously associate each amino acid with a local coordinate system and construct rotation-equivariant spherical filters that operate on angular information between graph nodes. Within the framework of the protein model quality assessment problem, we demonstrate that the proposed spherical convolution method significantly improves the quality of model assessment compared to the standard message-passing approach. It is also comparable to state-of-the-art methods, as we demonstrate on Critical Assessment of Structure Prediction (CASP) benchmarks. The proposed technique operates only on geometric features of protein 3D models. This makes it universal and applicable to any other geometric-learning task where the graph structure allows constructing local coordinate systems.
{"title":"Spherical convolutions on molecular graphs for protein model quality assessment","authors":"Ilia Igashov, Nikita Pavlichenko, S. Grudinin","doi":"10.1088/2632-2153/ABF856","DOIUrl":"https://doi.org/10.1088/2632-2153/ABF856","url":null,"abstract":"Processing information on 3D objects requires methods stable to rigid-body transformations, in particular rotations, of the input data. In image processing tasks, convolutional neural networks achieve this property using rotation-equivariant operations. However, contrary to images, graphs generally have irregular topology. This makes it challenging to define a rotation-equivariant convolution operation on these structures. In this work, we propose Spherical Graph Convolutional Network (S-GCN) that processes 3D models of proteins represented as molecular graphs. In a protein molecule, individual amino acids have common topological elements. This allows us to unambiguously associate each amino acid with a local coordinate system and construct rotation-equivariant spherical filters that operate on angular information between graph nodes. Within the framework of the protein model quality assessment problem, we demonstrate that the proposed spherical convolution method significantly improves the quality of model assessment compared to the standard message-passing approach. It is also comparable to state-of-the-art methods, as we demonstrate on Critical Assessment of Structure Prediction (CASP) benchmarks. The proposed technique operates only on geometric features of protein 3D models. This makes it universal and applicable to any other geometric-learning task where the graph structure allows constructing local coordinate systems.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"20 1","pages":"45005"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90650751","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 : 2020-10-13DOI: 10.1088/2632-2153/ac0616
Carlos Bravo-Prieto
We present the enhanced feature quantum autoencoder, or EF-QAE, a variational quantum algorithm capable of compressing quantum states of different models with higher fidelity. The key idea of the algorithm is to define a parameterized quantum circuit that depends upon adjustable parameters and a feature vector that characterizes such a model. We assess the validity of the method in simulations by compressing ground states of the Ising model and classical handwritten digits. The results show that EF-QAE improves the performance compared to the standard quantum autoencoder using the same amount of quantum resources, but at the expense of additional classical optimization. Therefore, EF-QAE makes the task of compressing quantum information better suited to be implemented in near-term quantum devices.
{"title":"Quantum autoencoders with enhanced data encoding","authors":"Carlos Bravo-Prieto","doi":"10.1088/2632-2153/ac0616","DOIUrl":"https://doi.org/10.1088/2632-2153/ac0616","url":null,"abstract":"We present the enhanced feature quantum autoencoder, or EF-QAE, a variational quantum algorithm capable of compressing quantum states of different models with higher fidelity. The key idea of the algorithm is to define a parameterized quantum circuit that depends upon adjustable parameters and a feature vector that characterizes such a model. We assess the validity of the method in simulations by compressing ground states of the Ising model and classical handwritten digits. The results show that EF-QAE improves the performance compared to the standard quantum autoencoder using the same amount of quantum resources, but at the expense of additional classical optimization. Therefore, EF-QAE makes the task of compressing quantum information better suited to be implemented in near-term quantum devices.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"86 1","pages":"35028"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76973011","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 : 2020-04-06DOI: 10.1088/2632-2153/ABF5B6
Jeffrey M. Ede
Compressed sensing is applied to scanning transmission electron microscopy to decrease electron dose and scan time. However, established methods use static sampling strategies that do not adapt to samples. We have extended recurrent deterministic policy gradients to train deep LSTMs and differentiable neural computers to adaptively sample scan path segments. Recurrent agents cooperate with a convolutional generator to complete partial scans. We show that our approach outperforms established algorithms based on spiral scans, and we expect our results to be generalizable to other scan systems. Source code, pretrained models and training data is available at this https URL.
{"title":"Adaptive Partial Scanning Transmission Electron Microscopy with Reinforcement Learning","authors":"Jeffrey M. Ede","doi":"10.1088/2632-2153/ABF5B6","DOIUrl":"https://doi.org/10.1088/2632-2153/ABF5B6","url":null,"abstract":"Compressed sensing is applied to scanning transmission electron microscopy to decrease electron dose and scan time. However, established methods use static sampling strategies that do not adapt to samples. We have extended recurrent deterministic policy gradients to train deep LSTMs and differentiable neural computers to adaptively sample scan path segments. Recurrent agents cooperate with a convolutional generator to complete partial scans. We show that our approach outperforms established algorithms based on spiral scans, and we expect our results to be generalizable to other scan systems. Source code, pretrained models and training data is available at this https URL.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"19 1","pages":"45011"},"PeriodicalIF":0.0,"publicationDate":"2020-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84665035","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：