scholarly journals Mechanism of amorphous phase stabilization in ultrathin films of monoatomic phase change material

Nanoscale ◽  
2021 ◽  
Author(s):  
Daniele Dragoni ◽  
Jörg Behler ◽  
Marco Bernasconi
Keyword(s):  
Machine Learning ◽  
Phase Change ◽  
Ultrathin Films ◽  
Large Scale ◽  
Interatomic Potential ◽  
Atomistic Simulations ◽  
Machine Learning Method ◽  
Learning Method ◽  
Phase Stabilization ◽  
Change Material

Large scale atomistic simulations with an interatomic potential generated by a machine learning method have been exploited to study the crystallization of Sb in ultrathin films.

scholarly journals Machine learning method for tight-binding Hamiltonian parameterization from ab-initio band structure

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Zifeng Wang ◽  
Shizhuo Ye ◽  
Hao Wang ◽  
Jin He ◽  
Qijun Huang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ab Initio ◽  
Large Scale ◽  
Tight Binding ◽  
Real Space ◽  
Machine Learning Method ◽  
Learning Method ◽  
Energy Bands ◽  
Physical Problems ◽  
Machine Learning Applications

AbstractThe tight-binding (TB) method is an ideal candidate for determining electronic and transport properties for a large-scale system. It describes the system as real-space Hamiltonian matrices expressed on a manageable number of parameters, leading to substantially lower computational costs than the ab-initio methods. Since the whole system is defined by the parameterization scheme, the choice of the TB parameters decides the reliability of the TB calculations. The typical empirical TB method uses the TB parameters directly from the existing parameter sets, which hardly reproduces the desired electronic structures quantitatively without specific optimizations. It is thus not suitable for quantitative studies like the transport property calculations. The ab-initio TB method derives the TB parameters from the ab-initio results through the transformation of basis functions, which achieves much higher numerical accuracy. However, it assumes prior knowledge of the basis and may encompass truncation error. Here, a machine learning method for TB Hamiltonian parameterization is proposed, within which a neural network (NN) is introduced with its neurons acting as the TB matrix elements. This method can construct the empirical TB model that reproduces the given ab-initio energy bands with predefined accuracy, which provides a fast and convenient way for TB model construction and gives insights into machine learning applications in physical problems.

Data Mining From Endmill Tool Catalog Information Based on the Use of a Machine Learning Method

2020 ◽  
Author(s):  
Akihito Asakura ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Hiroyuki Kodama
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Large Scale ◽  
Manufacturing Industry ◽  
New Technologies ◽  
Cutting Conditions ◽  
Machine Learning Method ◽  
Learning Method ◽  
Large Scale Data ◽  
Recent Computer

Abstract In recent years, the needs associated with the development of new technologies in the manufacturing industry that utilize big data typified by the Internet-of-Things (IoT) and artificial intelligence (AI) have been increasing. Recent computer-aided manufacturing (CAM) systems have evolved so that unskilled technicians can create tool paths relatively easily with numerically controlled (NC) programs, but tool-cutting conditions used for machining cannot be automatically determined. Therefore, many unskilled technicians often set the cutting conditions based on the recommended conditions described in the tool catalog. However, given that the catalog contains large-scale data on machining technology, setting the proper conditions becomes a time-consuming and inefficient process. In this study, we aimed to construct a system to support unskilled technicians to determine the optimum machining conditions. To this end, we constructed a prediction model using a random forest machine learning method to predict the cutting conditions. It was confirmed that the prediction with the random forest method can be performed with high accuracy based on the cutting conditions recommended by the tool maker. Thus, the effectiveness of this method was verified.

Development of Neural-Network Interatomic Potentials for Structural Materials

2016 ◽  
Vol 258 ◽  
pp. 69-72
Author(s):  
Ryo Kobayashi ◽  
Tomoyuki Tamura ◽  
Ichiro Takeuchi ◽  
Shuji Ogata
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Md Simulation ◽  
Interatomic Potential ◽  
Basis Functions ◽  
Interatomic Potentials ◽  
Machine Learning Method ◽  
Learning Method ◽  
New Approach ◽  
The Neural Network

The validity of the molecular dynamics (MD) simulation is highly dependent on the accuracy or reproducibility of interatomic potentials used in the MD simulation. The neural-network (NN) interatomic potential is one of promising interatomic potentials based on machine-learning method. However, there are some parameters that should be determined heuristically before making the NN potential, such as the shape and number of basis functions. We have developed a new approach to select only relevant basis functions from a lot of candidates systematically and less heuristically without loosing the accuracy of the potential. The present NN potential for Si system shows very good agreements with the results obtained using ab-initio calculations.

Atomistic Simulations of Phase Change Materials for Electronic Memories

2019 ◽  
Vol 18 (03n04) ◽  
pp. 1940082
Author(s):  
M. Bernasconi
Keyword(s):  
Phase Change ◽  
Density Functional ◽  
Large Scale ◽  
Phase Change Materials ◽  
Interatomic Potential ◽  
Supercooled Liquid ◽  
Atomistic Simulations ◽  
Artificial Neural Network Method ◽  
Dynamics Simulations ◽  
Methodological Advance

We review our results on large-scale atomistic simulations of the phase change compound GeTe of interest for applications in nonvolatile electronic memories. The simulations are based on an interatomic potential with an accuracy close to that of the density functional theory (DFT). The potential was generated by fitting a DFT database by means of an artificial neural network method. This methodological advance allowed us to perform molecular dynamics simulations with several thousand atoms for several ns that provided useful insights on several properties of interest for the operation of phase change memories, including the crystallization kinetics, the dynamics of the supercooled liquid, the structural relaxation in the glass and the properties of nanowires.

scholarly journals Evaluation of COVID-19 Pandemic in Six Asia-Pacific Countries using Data-Driven and Machine Learning Method Based on the Current Management and Interventions

2021 ◽  
Author(s):  
Shuang Ao ◽  
Wenbo Huang ◽  
Dan Han ◽  
Yuming Liu ◽  
Shuang Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Data Driven ◽  
Asia Pacific ◽  
Machine Learning Method ◽  
Learning Method ◽  
Current Management ◽  
Large Populations ◽  
The Government ◽  
Using Data

Abstract Background South-east Asia and Western Pacific countries have large populations and underreporting of Covid19, which pose challenges to the large-scale response. Methods Data-driven methods are used to evaluate the Government or society’s interventions and the situation of the COVID-19 pandemic, and machine learning method are used to forecast the trend of COVID-19 pandemic based on the current management and interventions. Results The results show that. India received low government response index scores in February, and the number of confirmed cases and active cases in September became quite high with large stock and the overall growth rate is higher than 1. The number of daily confirmed cases in Bangladesh, Japan and Philippines is low and on the decline, it is rising in Malaysia and Indonesia. The number of active cases in Bangladesh, Japan, India and Bangladesh has begun to decline, Malaysia and Indonesia is no sign of decline. Bangladesh, Japan and Philippines will be flat or moderating, while Malaysia and Indonesia will still have no slowdown momentum and the situation will be severe. Conclusions The results show that the existing management and interventions responses are effective, although they have room for improvement, and Malaysia and Indonesia need to be improved and strengthened.

Speech Organ Contour Extraction Using Real-Time MRI and Machine Learning Method

2019 ◽  
Author(s):  
Hironori Takemoto ◽  
Tsubasa Goto ◽  
Yuya Hagihara ◽  
Sayaka Hamanaka ◽  
Tatsuya Kitamura ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Machine Learning Method ◽  
Learning Method ◽  
Contour Extraction
Sign in / Sign up

Export Citation Format

Share Document