skip to main content

Search for: All records

Award ID contains: 2118201

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Free, publicly-accessible full text available June 13, 2023
  2. Projection algorithms such as t-SNE or UMAP are useful for the visualization of high dimensional data, but depend on hyperpa- rameters which must be tuned carefully. Unfortunately, iteratively recomputing projections to find the optimal hyperparameter values is computationally intensive and unintuitive due to the stochastic nature of such methods. In this paper we propose Hy- perNP, a scalable method that allows for real-time interactive hyperparameter exploration of projection methods by training neural network approximations. A HyperNP model can be trained on a fraction of the total data instances and hyperparameter configurations that one would like to investigate and can compute projections for new data and hyperparameters at interactive speeds. HyperNP models are compact in size and fast to compute, thus allowing them to be embedded in lightweight visualiza- tion systems. We evaluate the performance of HyperNP across three datasets in terms of performance and speed. The results suggest that HyperNP models are accurate, scalable, interactive, and appropriate for use in real-world settings.
    Free, publicly-accessible full text available June 13, 2023
  3. Free, publicly-accessible full text available April 26, 2023
  4. Parametric computer-aided design (CAD) tools are the predominant way that engineers specify physical structures, from bicycle pedals to airplanes to printed circuit boards. The key characteristic of parametric CAD is that design intent is encoded not only via geometric primitives, but also by parameterized constraints between the elements. This relational specification can be viewed as the construction of a constraint program, allowing edits to coherently propagate to other parts of the design. Machine learning offers the intriguing possibility of accelerating the de- sign process via generative modeling of these structures, enabling new tools such as autocompletion, constraint inference, and conditional synthesis. In this work, we present such an approach to generative modeling of parametric CAD sketches, which constitute the basic computational building blocks of modern mechanical design. Our model, trained on real-world designs from the SketchGraphs dataset, autoregressively synthesizes sketches as sequences of primitives, with initial coordinates, and constraints that reference back to the sampled primitives. As samples from the model match the constraint graph representation used in standard CAD software, they may be directly imported, solved, and edited according to down- stream design tasks. In addition, we condition the model on various contexts, including partial sketches (primers) and imagesmore »of hand-drawn sketches. Evaluation of the proposed approach demonstrates its ability to synthesize realistic CAD sketches and its potential to aid the mechanical design workflow.« less
    Free, publicly-accessible full text available April 28, 2023
  5. Free, publicly-accessible full text available February 22, 2023
  6. Azoarene photoswitches are versatile molecules that interconvert from their E-isomer to their Z-isomer with light. Azobenzene is a prototypical photoswitch but its derivatives can be poorly suited for in vivo applications such as photopharmacology due to undesired photochemical reactions promoted by ultraviolet light and the relatively short half-life (t1/2) of the Z-isomer (2 days). Experimental and computational studies suggest that these properties (λmax of the E isomer and t1/2 of the Z-isomer) are inversely related. We identified isomeric azobisthiophenes and azobisfurans from a high-throughput screening study of 1540 azoarenes as photoswitch candidates with improved λmax and t1/2 values relative to azobenzene. We used density functional theory to predict the activation free energies and vertical excitation energies of the E- and Z-isomers of 2,2- and 3,3-substituted azobisthiophenes and azobisfurans. The half-lives depend on whether the heterocycles are π-conjugated or cross-conjugated with the diazo π-bond. The 2,2-substituted azoarenes both have t1/2 values on the scale of 1 hour, while the 3,3-analogues have computed half-lives of 40 and 230 years (thiophene and furan, respectively). The 2,2-substituted heteroazoarenes have significantly higher λmax absorptions than their 3,3-substituted analogues: 76 nm for azofuran and 77 nm for azothiophene.