• Corpus ID: 227151680

AI Discovering a Coordinate System of Chemical Elements: Dual Representation by Variational Autoencoders

@article{Glushkovsky2020AIDA,
  title={AI Discovering a Coordinate System of Chemical Elements: Dual Representation by Variational Autoencoders},
  author={Alex Glushkovsky},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.12090}
}
The periodic table is a fundamental representation of chemical elements that plays essential theoretical and practical roles. The research article discusses the experiences of unsupervised training of neural networks to represent elements on the 2D latent space based on their electron configurations while forcing disentanglement. To emphasize chemical properties of the elements, the original data of electron configurations has been realigned towards the outermost valence orbitals. Recognizing… 

Ab Initio Machine Learning in Chemical Compound Space

While state-of-the-art approximations to quantum problems impose severe computational bottlenecks, recent QML based developments indicate the possibility of substantial acceleration without sacrificing the predictive power of quantum mechanics.

Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies

This work uses Natural Evolution Strategies (NES), a class of gradient-free black-box optimization algorithms, to learn discrete structured VAEs, and demonstrates empirically that optimizing discrete structuredVAEs using NES is as effective as gradient-based approximations.

Designing Complex Experiments by Applying Unsupervised Machine Learning

The article discusses the application of unsupervised machine learning to support the pragmatic designs of complex experiments by developing a beta variational autoencoder to represent trials of the initial full factorial design.

L EARNING D ISCRETE S TRUCTURED V ARIATIONAL A UTO -E NCODER USING N ATURAL E VOLUTION S TRATEGIES

This work uses Natural Evolution Strategies (NES), a class of gradient-free black-box optimization algorithms, to learn discrete structured VAEs, and demonstrates empirically that optimizing discrete structuredVAEs using NES is as effective as gradient-based approximations.

Quantum Machine Learning in Chemical Compound Space

The case is made for quantum machine learning: An inductive molecular modeling approach which can be applied to quantum chemistry problems.

References

SHOWING 1-10 OF 48 REFERENCES

AI Giving Back to Statistics? Discovery of the Coordinate System of Univariate Distributions by Beta Variational Autoencoder

Experiences of training neural networks to classify univariate empirical distributions and to represent them on the two-dimensional latent space forcing disentanglement based on the inputs of cumulative distribution functions (CDF) are discussed.

Feature optimization for atomistic machine learning yields a data-driven construction of the periodic table of the elements.

This work shows how one can generalize the SOAP kernel to introduce a distance-dependent weight that accounts for the multi-scale nature of the interactions, and a description of correlations between chemical species, to improve substantially the performance of ML models of molecular and materials stability.

Recreation of the periodic table with an unsupervised machine learning algorithm

The PTG is an unsupervised machine learning algorithm based on the generative topographic mapping, which can automate the translation of high-dimensional data into a tabular form with varying layouts on-demand and showed what the PTG learned from the element data and how the element features are compressed to the lower-dimensional latent spaces.

Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder

This work presents a quantitative assessment of the latent space in terms of its predictive ability for organic molecules in the QM9 dataset and considers a Bayesian formalism to account for the limited size training data set.

Atom2Vec: learning atoms for materials discovery

It is shown that the unsupervised machines (Atom2Vec) can learn the basic properties of atoms by themselves from the extensive database of known compounds and materials.

Periodic Table of the Elements in the Perspective of Artificial Neural Networks

A self-organized map with information available at Mendeleev’s time is used and shows that similar elements tend to form individual clusters, which means that although SOM generates clusters of halogens, alkaline metals, and transition metals that show a similarity with the periodic table of elements, the SOM did not achieve the sophistication that Mendeleeva achieved.

Learning atoms for materials discovery

The unsupervised machines (Atom2Vec) can learn the basic properties of atoms by themselves from the extensive database of known compounds and materials, represented in terms of high-dimensional vectors, and clustering of atoms in vector space classifies them into meaningful groups consistent with human knowledge.

beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework

Learning an interpretable factorised representation of the independent data generative factors of the world without supervision is an important precursor for the development of artificial

Deep learning for molecular design—a review of the state of the art

Several important high level themes emerge, including the shift away from the SMILES string representation of molecules towards more sophisticated representations such as graph grammars and 3D representations, the importance of reward function design, the need for better standards for benchmarking and testing, and the benefits of adversarial training and reinforcement learning over maximum likelihood based training.

ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition

The design and implementation of a deep neural network model referred to as ElemNet is presented; it automatically captures the physical and chemical interactions and similarities between different elements using artificial intelligence which allows it to predict the materials properties with better accuracy and speed.