Deep learning approach for image classification of magnetic phases in chiral magnets

Salcedo-Gallo, J. S.; Galindo-González, Cristian Camilo

doi:10.1016/j.jmmm.2020.166482

Cited by 16 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The custom architecture used here is similar to that of LeNet-5 [23]. A comparable custom architecture has been used for other analyses of magnetic systems [12,15]. The network structure was chosen after varying the number of convolutional and fully connected layers, the filter and kernel size, the number of neurons, and the activation function.…”

Section: Neural Network-driven Characterization Of Skyrmion Ensembles...mentioning

confidence: 99%

“…Meanwhile, many complex problems have been solved using machine learning techniques. Particularly, machine learning algorithms have been used for finding [10], recognizing [11], and classifying [12] ground states of systems with Dzyaloshinskii-Moriya interactions (DMI) and for reconstructing the spin configuration from data obtained in reciprocal space [13]. Machine learning has also been used to define phase transitions in Ising-like spin systems [14] and to estimate the DMI parameters from images of magnetic domains [15,16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Topological characterization of dynamic chiral magnetic textures using machine learning

Matthies,

Schäffer,

Posske

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently proposed spintronic devices use magnetic skyrmions as bits of information. The reliable detection of those chiral magnetic objects is an indispensable requirement. Yet, the high mobility of magnetic skyrmions leads to their stochastic motion at finite temperatures, which hinders the precise measurement of the topological numbers. Here, we demonstrate the successful training of artificial neural networks to reconstruct the skyrmion number in confined geometries from timeintegrated, dimensionally reduced data. Our results prove the possibility to recover the topological charge from a time-averaged measurement and hence smeared dynamic skyrmion ensemble, which is of immediate relevance to the interpretation of experimental results, skyrmion-based computing, and memory concepts.

show abstract

Section: Neural Network-driven Characterization Of Skyrmion Ensembles...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Topological characterization of dynamic chiral magnetic textures using machine learning

Matthies,

Schäffer,

Posske

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Lastly, it is worth noting that although the focus of this text is mainly on engineering hard and soft magnetic materials, AI has also been implemented in activities scrutinizing other relevant topics, such as chiral magnets [31], 2D magnets [32], and ferromagnetic compounds [33].…”

Section: Ai-engineering Hard and Soft Magnetic Materials: Summarizing The Present And Future Directionsmentioning

confidence: 99%

Artificial Intelligence—Engineering Magnetic Materials: Current Status and a Brief Perspective

Périgo¹,

Faria

2021

Magnetochemistry

View full text Add to dashboard Cite

The implementation of artificial intelligence into the research and development of (currently) the most economically relevant classes of engineering hard and soft magnetic materials is addressed. Machine learning is nowadays the key approach utilized in the discovery of new compounds, physical–chemical properties prediction, microstructural/magnetic characterization, and applicability of permanent magnets and crystalline/amorphous soft magnetic alloys. Future opportunities are envisioned on at least two fronts: (a) ultra-low losses materials, as well as processes that enable their manufacturing, unlocking the next step for higher efficiency electrification, power conversion, and distribution; (b) additively manufactured magnetic materials by predicting and developing novel powdered materials properties, generative design concepts, and optimal processing conditions.

show abstract

“…In fact, neural networks have been implemented in the last years to distinguish skyrmion phases. On one hand, a few years ago, it was shown that a single layer neural network can succesfully classify standard configurations: spiral, ferromagnetic and skyrmion crystal 16 , and a similar classification task was achieved with convolutional neural networks (CNNs) to construct low temperature phase diagrams for models including anisotropy terms 17 . On the other hand, CNNs were used to predict features such as chirality in these type of systems 18 , even in confined geometries 19 , and to extract information on the interactions from data images 20 .…”

Section: Introductionmentioning

confidence: 99%

Machine learning techniques to construct detailed phase diagrams for skyrmion systems

Albarracín,

Rosales

2022

Preprint

View full text Add to dashboard Cite

Recently, there has been an increased interest in the application of machine learning (ML) techniques to a variety of problems in condensed matter physics. In this regard, of particular significance is the characterization of simple and complex phases of matter. Here, we use a ML approach to construct the full phase diagram of a well known spin model combining ferromagnetic exchange and Dzyaloshinskii-Moriya (DM) interactions where topological phases emerge. At low temperatures, the system is tuned from a spiral phase to a skyrmion crystal by a magnetic field. However, thermal fluctuations induce two types of intermediate phases, bimerons and skyrmion gas, which are not as easily determined as spirals or skyrmion crystals. We resort to large scale Monte Carlo simulations to obtain low temperature spin configurations, and train a convolutional neural network (CNN), taking only snapshots at specific values of the DM couplings, to classify between the different phases, focusing on the intermediate and intricate topological textures. We then apply the CNN to higher temperature configurations and to other DM values, to construct a detailed magnetic field-temperature phase diagram, achieving outstanding results. We discuss the importance of including the disordered paramagnetic phases in order to get the phase boundaries, and finally, we compare our approach with other ML algorithms.

show abstract

Deep learning approach for image classification of magnetic phases in chiral magnets

Cited by 16 publications

References 14 publications

Topological characterization of dynamic chiral magnetic textures using machine learning

Topological characterization of dynamic chiral magnetic textures using machine learning

Artificial Intelligence—Engineering Magnetic Materials: Current Status and a Brief Perspective

Machine learning techniques to construct detailed phase diagrams for skyrmion systems

Contact Info

Product

Resources

About