ClasSOMfier: A neural network for cluster analysis and detection of lattice defects

Troncoso, Javier F.

doi:10.1016/j.commatsci.2020.110167

Search citation statements

Order By: Relevance

Paper Sections

Select...

B Counter Propagation Artificial Neural Network1

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2023

Publication Types

Select...

Article4

Other1

Relationship

Self Cite0

Independent5

Authors

Journals

Cited by 5 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second layer is named the Kohonen Self-Organizing Map (K-SOM) and is among the Artificial Neural Network models. Moreover, the K-SOM is the best-known and commonly used in data classification and clustering [38], [39].…”

Section: B Counter Propagation Artificial Neural Networkmentioning

confidence: 99%

A Novel Strategy for Improving the Counter Propagation Artificial Neural Networks in Classification Tasks

Belattar

Abdoun

Haimoudi

2022

JCOMSS

View full text Add to dashboard Cite

Section: B Counter Propagation Artificial Neural Networkmentioning

confidence: 99%

A Novel Strategy for Improving the Counter Propagation Artificial Neural Networks in Classification Tasks

Belattar

Abdoun

Haimoudi

2022

JCOMSS

View full text Add to dashboard Cite

“…The most frequently used descriptors of local atomic environments are Coulomb matrices [42], sine matrices [43], atomic-centered symmetry functions [44], and smooth overlap of atomic orbitals (SOAP) [45]. These descriptors are invariant to rotations, translations, and permutations of atoms, and can be used in combination with unsupervised learning algorithms to identify structural building blocks of grain boundaries [46,47,48].…”

Section: Introductionmentioning

confidence: 99%

Machine learning of twin/matrix interfaces from local stress field

Troncoso¹,

Yang²,

Ventura³

et al. 2023

Preprint

View full text Add to dashboard Cite

Twinning is an important deformation mode in plastically deformed hexagonal close-packed materials. The extremely high twin growth rates at the nanoscale make atomistic simulations an attractive method for investigating the role of individual twin/matrix interfaces such as twin boundaries and basal-prismatic interfaces in twin growth kinetics. Unfortunately, there is no single framework that allows researchers to differentiate such interfaces automatically, neither in experimental in-situ transmission electron microscopy analysis images nor in atomistic simulations. Moreover, the presence of alloying elements introduces substantial noise to local atomic environments, making it nearly impossible to identify which atoms belong to which interface. Here, with the help of advanced machine learning methods, we provide a proof-of-concept way of using the local stress field distribution as an indicator for the presence of interfaces and for determining their types. We apply such an analysis to the growth of twin embryos in Mg-10 at.% Al alloys under constant stress and constant strain conditions, corresponding to two extremes of high and low strain rates, respectively. We discover that the kinetics of such growth is driven by high-energy basal-prismatic interfaces, in line with our experimental observations for pure Mg.

show abstract