DLHub: Model and Data Serving for Science

Chard, Ryan; Li, Zhuozhao; Chard, Kyle; Ward, Logan; Babuji, Yadu; Woodard, A.; Tuecke, Steven; Blaiszik, Ben; Franklin, Michael; Foster, Ian

doi:10.1109/ipdps.2019.00038

Cited by 71 publications

(61 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SchNet Delta and FCHL Delta models are available for anyone to use via DLHub. [15] DLHub's simple Python interface takes the XYZ coordinates of a molecule and returns the G4MP2 atomization enthalpy; it runs models on cloud or cluster resources, eliminating the need to understand how to use QML or SchNetPack or even to install them. We hope that by publishing the models in this way, we will enable others to integrate the capabilities developed in this work in their own research.…”

Section: Recommendationsmentioning

confidence: 99%

“…[14] We examine how to integrate information from low-cost B3LYP calculations into each method and find that both techniques predict atomization energies of molecules larger than our training set with errors below 0.04 eV using a Δ-learning approach. We have created a simple interface to allow others to use our bestperforming models by publishing them on DLHub, [15] so that accurate atomization energies are readily accessible to the materials and chemistry community at large.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning prediction of accurate atomization energies of organic molecules from low-fidelity quantum chemical calculations

et al. 2019

Self Cite

View full text Add to dashboard Cite

Recent studies illustrate how machine learning (ML) can be used to bypass a core challenge of molecular modeling: the tradeoff between accuracy and computational cost. Here, we assess multiple ML approaches for predicting the atomization energy of organic molecules. Our resulting models learn the difference between low-fidelity, B3LYP, and high-accuracy, G4MP2, atomization energies, and predict the G4MP2 atomization energy to 0.005 eV (mean absolute error) for molecules with less than 9 heavy atoms and 0.012 eV for a small set of molecules with between 10 and 14 heavy atoms. Our two best models, which have different accuracy/speed tradeoffs, enable the efficient prediction of G4MP2-level energies for large molecules and are available through a simple web interface.

show abstract

Section: Recommendationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine learning prediction of accurate atomization energies of organic molecules from low-fidelity quantum chemical calculations

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…e proposed deep learning model and design insights gained from this work can be used in building predictive models for other applications with vector inputs. e code repository is available at h ps://github.com/dipendra009/IRNet; we also plan to make the models described in this work available via DLHub [9].…”

Section: Discussionmentioning

confidence: 99%

IRNet

Jha

Ward

Yang

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

Self Cite

View full text Add to dashboard Cite

Materials discovery is crucial for making scienti c advances in many domains. Collections of data from experiments and rstprinciple computations have spurred interest in applying machine learning methods to create predictive models capable of mapping from composition and crystal structures to materials properties. Generally, these are regression problems with the input being a 1D vector composed of numerical a ributes representing the material composition and/or crystal structure. While neural networks consisting of fully connected layers have been applied to such problems, their performance o en su ers from the vanishing gradient problem when network depth is increased. Hence, predictive modeling for such tasks has been mainly limited to traditional machine learning techniques such as Random Forest. In this paper, we study and propose design principles for building deep regression networks composed of fully connected layers with numerical vectors as input. We introduce a novel deep regression network with individual residual learning, IRNet, that places shortcut connections a er each layer so that each layer learns the residual mapping between its output and input. We use the problem of learning properties of inorganic materials from numerical a ributes derived from material composition and/or crystal structure to compare IRNet's performance against that of other machine learning techniques. Using multiple datasets from the Open antum Materials Database (OQMD) and Materials Project for training and evaluation, we show that IRNet provides signi cantly be er prediction performance than the stateof-the-art machine learning approaches currently used by domain ACM acknowledges that this contribution was authored or co-authored by an employee, or contractor of the national government. As such, the Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only. Permission to make digital or hard copies for personal or classroom use is granted. Copies must bear this notice and the full citation on the rst page. Copyrights for components of this work owned by others than ACM must be honored. To copy otherwise, distribute, republish, or post, requires prior speci c permission and/or a fee. Request permissions from permissions@acm.org.

show abstract

“…Once the GAN model is trained, we can input a noisy image to the generator and it outputs the corresponding enhanced image. In practice, we save the generator and publish it on the DLHub [43] to serve for users.…”

Section: Generator Lossmentioning

confidence: 99%

TomoGAN: low-dose synchrotron x-ray tomography with generative adversarial networks: discussion

et al. 2020

Self Cite

View full text Add to dashboard Cite

Synchrotron-based x-ray tomography is a noninvasive imaging technique that allows for reconstructing the internal structure of materials at high spatial resolutions from tens of micrometers to a few nanometers. In order to resolve sample features at smaller length scales, however, a higher radiation dose is required. Therefore, the limitation on the achievable resolution is set primarily by noise at these length scales. We present TomoGAN, a denoising technique based on generative adversarial networks, for improving the quality of reconstructed images for low-dose imaging conditions. We evaluate our approach in two photon-budget-limited experimental conditions: (1) sufficient number of low-dose projections (based on Nyquist sampling), and (2) insufficient or limited number of high-dose projections. In both cases the angular sampling is assumed to be isotropic, and the photon budget throughout the experiment is fixed based on the maximum allowable radiation dose on the sample. Evaluation with both simulated and experimental datasets shows that our approach can significantly reduce noise in reconstructed images, improving the structural similarity score of simulation and experimental data from 0.18 to 0.9 and from 0.18 to 0.41, respectively. Furthermore, the quality of the reconstructed images with filtered back projection followed by our denoising approach exceeds that of reconstructions with the simultaneous iterative reconstruction technique, showing the computational superiority of our approach.

show abstract

DLHub: Model and Data Serving for Science

Cited by 71 publications

References 28 publications

Machine learning prediction of accurate atomization energies of organic molecules from low-fidelity quantum chemical calculations

Machine learning prediction of accurate atomization energies of organic molecules from low-fidelity quantum chemical calculations

IRNet

TomoGAN: low-dose synchrotron x-ray tomography with generative adversarial networks: discussion

Contact Info

Product

Resources

About