2019
DOI: 10.1021/acs.jctc.8b01285
|View full text |Cite
|
Sign up to set email alerts
|

Evolutionary Approach to Constructing a Deep Feedforward Neural Network for Prediction of Electronic Coupling Elements in Molecular Materials

Abstract: We present a general framework for the construction of a deep feedforward neural network (FFNN) to predict distance and orientation dependent electronic coupling elements in disordered molecular materials. An evolutionary algorithm automatizes the selection of an optimal architecture of the artificial neural network within a predefined search space. Systematic guidance, beyond minimizing the model error with stochastic gradient descent based backpropagation, is provided by simultaneous maximization of a model … Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

2
43
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
6
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 29 publications
(45 citation statements)
references
References 46 publications
2
43
0
Order By: Relevance
“…Within the context of charge transport simulations, ML has been successfully used to predict reorganization energies and transfer integrals in different organic semiconductors. In our previous work, we used kernel ridge regression (KRR) to predict transfer integrals in thermally disordered pentacene crystals using system specific geometric features .…”
Section: Introductionmentioning
confidence: 99%
“…Within the context of charge transport simulations, ML has been successfully used to predict reorganization energies and transfer integrals in different organic semiconductors. In our previous work, we used kernel ridge regression (KRR) to predict transfer integrals in thermally disordered pentacene crystals using system specific geometric features .…”
Section: Introductionmentioning
confidence: 99%
“…The application of Kernel Ridge Regression (KRR) models to predicting molecular quantum properties has been very successful over recent years [8,14,15,20,41]. The main idea relies on constructing a kernel matrix with a kernel function k that can quantitatively measure similarity between molecular representations x i and x j , which are vector representations that encode the molecular physics [6,21,24]. The Laplacian kernel function, for example, is described as…”
Section: B Kernel Ridge Regressionmentioning
confidence: 99%
“…Hence, the incorporation of quantum machine learning (QML) has been gaining great traction over recent years. QML based surrogate property models have become a popular alternative approach for their fast, reliable, and accurate predictions of molecular and material properties [1][2][3][4][5][6][7][8][9][10][11][12][13][14].…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…For excited state properties, in general, the error rates in QML have been noted to be inferior compared to that of ground state properties [61][62][63][64]. Yet, QML methods continue to find applications in excited state modeling in chemical space datasets [50,[65][66][67] as well as in potential surface manifolds [68][69][70][71][72][73]. Keeping abreast with the progress in QML, materials/molecules inverse-design protocols have also advanced since the earliest implementation nearly twenty years ago [74].…”
Section: Introductionmentioning
confidence: 99%