Artificial neural network potentials

Artificial neural network potentials (ANNP)

Example

The output of a feedforward NN, having a single layer of hidden neurons, each having a sigmoid activation function and a linear output neuron, is given by:

g (x, w) = \sum_{i = 1}^{N_{c}} [w_{N_{C} + 1, i} \tanh (\sum_{j = 1}^{n} w_{i, j} x_{j} + w_{i 0})] + w_{N_{c} + 1, 0}

Applications

ANNS have been sucessfully developed for water ^[1] aqueous NaOH solutions ^[2] gold nanoparticles ^[3].

References

↑ Tobias Morawietz, Andreas Singraber, Christoph Dellago, and Jörg Behler "How van der Waals interactions determine the unique properties of water", PNAS 113 pp. 8368-8373 (2016)
↑ Matti Hellström and Jörg Behler "Structure of aqueous NaOH solutions: insights from neural-network-based molecular dynamics simulations", Physical Chemistry Chemical Physics 19 pp. 82-96 (2017)
↑ Siva Chiriki, Shweta Jindal, and Satya S. Bulusu "Neural network potentials for dynamics and thermodynamics of gold nanoparticles", Journal of Chemical Physics 146 084314 (2017)

Related reading

[1] Tobias Morawietz, Andreas Singraber, Christoph Dellago, and Jörg Behler "How van der Waals interactions determine the unique properties of water", PNAS 113 pp. 8368-8373 (2016)

[2] Matti Hellström and Jörg Behler "Structure of aqueous NaOH solutions: insights from neural-network-based molecular dynamics simulations", Physical Chemistry Chemical Physics 19 pp. 82-96 (2017)

[3] Siva Chiriki, Shweta Jindal, and Satya S. Bulusu "Neural network potentials for dynamics and thermodynamics of gold nanoparticles", Journal of Chemical Physics 146 084314 (2017)

[1]

[2]

[3]

Artificial neural network potentials

Example

Applications

References

Navigation menu

Search