QUANTUM COMPUTING CLUSTER ON THE BASIS OF 29Si CHAINS

Podryabinkin, D. A.; Danilyuk, A. L.

doi:10.1142/9789812701947_0071

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various techniques for improving the accuracy and transferability of general purpose ML potentials have been employed. Active learning methods 16,17 , which provide a consistent and automated improvement in accuracy and transferability, have contributed greatly to the success of general purpose models. An active learning algorithm achieves this by deciding what new QM calculations should be performed then adding the new data to the training dataset.…”

Section: Introductionmentioning

confidence: 99%

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

Zubatyuk¹,

Smith²,

Leszczyński³

et al. 2018

Preprint

View full text Add to dashboard Cite

Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.

show abstract

Section: Introductionmentioning

confidence: 99%

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

Zubatyuk¹,

Smith²,

Leszczyński³

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Although many ML predictions are capable of reaching beyond the chemical accuracy, 39,46,67,68 both the energy and forces of some configurations in new regions on PES, where the samples in the existing database are insufficient, are unreliable using the current ML model. A systematic and effective approach to detect such new configurations is necessary.…”

Section: Methodsmentioning

confidence: 99%

Solvation Free Energy Calculations with Quantum Mechanics/Molecular Mechanics and Machine Learning Models

2018

View full text Add to dashboard Cite

For exploration of chemical and biological systems, the combined quantum mechanics and molecular mechanics (QM/MM) and machine learning (ML) models have been developed recently to achieve high accuracy and efficiency for molecular dynamics (MD) simulations. Despite its success on reaction free energy calculations, how to identify new configurations on insufficiently sampled regions during MD and how to update the current ML models with the growing database on-the-fly are both very important but still challenging. In this letter, we apply the QM/MM ML method to solvation free energy calculations and address these two challenges. We employ three approaches to detect new data points and introduce the gradient boosting algorithm to reoptimize efficiently the ML model during ML-based MD sampling. The solvation free energy calculations on several typical organic molecules demonstrate that our developed method provides a systematic, robust and efficient way to explore new chemistry using ML-based QM/MM MD simulations.

show abstract

“…In AL the performance of a supervised ML model can be maximized with fewer labeled data if the ML model can choose data for the next training step from those learned in previous training steps. AL schemes have been successfully integrated in quantum chemistry, in combination with molecular dynamics [55][56][57] and for materials discovery, 58 especially when unlabeled data (e.g., new atomic configurations or new crystal structures) can be easily generated, while labeling of the data is difficult and time-consuming (e.g., obtaining quantummechanical (QM) properties via ab initio calculations).…”

Section: Introductionmentioning

confidence: 99%

Active Learning Configuration Interaction for Excited States Calculations of Polycyclic Aromatic Hydrocarbons

Jeong

Gaggioli

Gagliardi

2021

Preprint

View full text Add to dashboard Cite

We present the active learning configuration interaction (ALCI) method for multiconfigurational calculations based on large active spaces. ALCI leverages the use of an active learning procedure to find important electronic configurations among the full configuration space generated within an active space.We tested it for the calculation of singlet-singlet excited states of acenes and pyrene, by using different machine learning algorithms. The ALCI method yields excitation energies within 0.2-0.3 eV from those obtained by traditional complete active space configuration interaction (CASCI) calculations (affordable for active spaces up to 16 electrons in 16 orbitals), by including only a small fraction of the CASCI configuration space in the calculations. For larger active spaces (up to 26 electrons in 26 orbitals), not affordable with traditional CI methods, ALCI captures the trends of experimental excitation energies.Overall ALCI provides satisfactory approximations to large active-space wave functions with up to ten orders of magnitude fewer configurations. These ALCI wave functions are promising and affordable starting points for subsequent second order perturbation theory or pair-density functional theory calculations.for example, 22 electrons in 22 orbitals, using massive parallelization have been reported. 28 Some approximations to reduce the number of configurations have been developed, including the restricted active space SCF (RASSCF), 29 the generalized active space SCF (GASSCF) 30 and the localized active space SCF (LASSCF). 31 In RASSCF and GASSCF subspaces of electrons and orbitals are chosen, and the maximum

show abstract

QUANTUM COMPUTING CLUSTER ON THE BASIS OF ²⁹Si CHAINS

Cited by 3 publications

References 0 publications

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

Solvation Free Energy Calculations with Quantum Mechanics/Molecular Mechanics and Machine Learning Models

Active Learning Configuration Interaction for Excited States Calculations of Polycyclic Aromatic Hydrocarbons

Contact Info

Product

Resources

About