Search

Crystal-structure phase mapping is a core, long-standing challenge in materials science that requires identifying crystal structures, or mixtures thereof, in synthesized materials. Materials science experts excel at solving simple systems but cannot solve complex systems, creating a major bottleneck in high-throughput materials discovery. Herein we show how to automate crystal-structure phase mapping. We formulate phase mapping as an unsupervised pattern demixing problem and describe how to solve it using Deep Reasoning Networks (DRNets). DRNets combine deep learning with constraint reasoning for incorporating scientific prior knowledge and consequently require only a modest amount of (unlabeled) data. DRNets compensate for the limited data by exploiting and magnifying the rich prior knowledge about the thermodynamic rules governing the mixtures of crystals with constraint reasoning seamlessly integrated into neural network optimization. DRNets are designed with an interpretable latent space for encoding prior-knowledge domain constraints and seamlessly integrate constraint reasoning into neural network optimization. DRNets surpass previous approaches on crystal-structure phase mapping, unraveling the Bi-Cu-V oxide phase diagram, and aiding the discovery of solar-fuels materials.

The Kepler telescope has discovered over 4,000 planets (candidates) by searching ? 200,000 stars over a wide range of distance (order of kpc) in our Galaxy. Characterizing the kinematic properties (e.g., Galactic component membership and kinematic age) of these Kepler targets (including the planet (candidate) hosts) is the first step towards studying Kepler planets in the Galactic context, which will reveal fresh insights into planet formation and evolution. In this paper, the second part of the Planets Across the Space and Time (PAST) series, by combining the data from LAMOST and Gaia and then applying the revised kinematic methods from PAST I, we present a catalog of kinematic properties(i.e., Galactic positions, velocities, and the relative membership probabilities among the thin disk, thick disk, Hercules stream, and the halo) as well as other basic stellar parameters for 35,835 Kepler stars. Further analyses of the LAMOST-Gaia-Kepler catalog demonstrate that our derived kinematic age reveals the expected stellar activity-age trend. Furthermore, we find that the fraction of thin(thick) disk stars increases (decreases) with the transiting planet multiplicity (Np = 0, 1, 2 and 3+) and the kinematic age decreases with Np, which could be a consequence of the dynamical evolution of planetary architecture with age. The LAMOST-Gaia-Kepler catalog will be useful for future studies on the correlations between the exoplanet distributions and the stellar Galactic environments as well as ages., Comment: Accepted for publication in Astronomical Journal, 19 pages, 9 figures, 5 tables. The full data of the LAMOST-Gaia-Kepler kinematic catalog (Table 3) will be published with the journal. If you need to use the data, please contact us via the email (jwxie@nju.edu.cn, dg1826003@smail.nju.edu.cn)

Interacting spin networks are fundamental to quantum computing. Data-based tomography of time-independent spin networks has been achieved, but an open challenge is to ascertain the structures of time-dependent spin networks using time series measurements taken locally from a small subset of the spins. Physically, the dynamical evolution of a spin network under time-dependent driving or perturbation is described by the Heisenberg equation of motion. Motivated by this basic fact, we articulate a physics-enhanced machine learning framework whose core is Heisenberg neural networks. In particular, we develop a deep learning algorithm according to some physics motivated loss function based on the Heisenberg equation, which "forces" the neural network to follow the quantum evolution of the spin variables. We demonstrate that, from local measurements, not only the local Hamiltonian can be recovered but the Hamiltonian reflecting the interacting structure of the whole system can also be faithfully reconstructed. We test our Heisenberg neural machine on spin networks of a variety of structures. In the extreme case where measurements are taken from only one spin, the achieved tomography fidelity values can reach about 90%. The developed machine learning framework is applicable to any time-dependent systems whose quantum dynamical evolution is governed by the Heisenberg equation of motion., Comment: 14 pages, 8 figures

The rapid growth of research in exploiting machine learning to predict chaotic systems has revived a recent interest in Hamiltonian Neural Networks (HNNs) with physical constraints defined by the Hamilton's equations of motion, which represent a major class of physics-enhanced neural networks. We introduce a class of HNNs capable of adaptable prediction of nonlinear physical systems: by training the neural network based on time series from a small number of bifurcation-parameter values of the target Hamiltonian system, the HNN can predict the dynamical states at other parameter values, where the network has not been exposed to any information about the system at these parameter values. The architecture of the HNN differs from the previous ones in that we incorporate an input parameter channel, rendering the HNN parameter--cognizant. We demonstrate, using paradigmatic Hamiltonian systems, that training the HNN using time series from as few as four parameter values bestows the neural machine with the ability to predict the state of the target system in an entire parameter interval. Utilizing the ensemble maximum Lyapunov exponent and the alignment index as indicators, we show that our parameter-cognizant HNN can successfully predict the route of transition to chaos. Physics-enhanced machine learning is a forefront area of research, and our adaptable HNNs provide an approach to understanding machine learning with broad applications., Comment: 12 pages, 9 figures

Over 4,000 exoplanets have been identified and thousands of candidates are to be confirmed. The relations between the characteristics of these planetary systems and the kinematics, Galactic components, and ages of their host stars have yet to be well explored. Aiming to addressing these questions, we conduct a research project, dubbed as PAST (Planets Across Space and Time). To do this, one of the key steps is to accurately characterize the planet host stars. In this paper, the Paper I of the PAST series, we revisit the kinematic method for classification of Galactic components and extend the applicable range of velocity ellipsoid from about 100 pc to 1, 500 pc from the sun in order to cover most known planet hosts. Furthermore, we revisit the Age-Velocity dispersion Relation (AVR), which allows us to derive kinematic age with a typical uncertainty of 10-20% for an ensemble of stars. Applying the above revised methods, we present a catalog of kinematic properties (i.e. Galactic positions, velocities, the relative membership probabilities among the thin disk, thick disk, Hercules stream, and the halo) as well as other basic stellar parameters for 2,174 host stars of 2,872 planets by combining data from Gaia, LAMOST, APOGEE, RAVE, and the NASA exoplanet archive. The revised kinematic method and AVR as well as the stellar catalog of kinematic properties and ages lay foundation for future studies on exoplanets from two dimensions of space and time in the Galactic context., Comment: 26 pages, 20 figure, 10 tables, Accepted for publication in ApJ. The full data of the planet kinematic catalog (Table 10) will be published with the journal. If you need to use the data, please contact us via the email (jwxie@nju.edu.cn, dg1826003@smail.nju.edu.cn)

Despite the potential benefits of assistive technologies (ATs) for people with various disabilities, only around 7% of Chinese with disabilities have had an opportunity to use ATs. Even for those who have used ATs, the abandonment rate was high. Although China has the world's largest population with disabilities, prior research exploring how ATs are used and perceived, and why ATs are abandoned have been conducted primarily in North America and Europe. In this paper, we present an interview study conducted in China with 26 people with various disabilities to understand their practices, challenges, perceptions, and misperceptions of using ATs. From the study, we learned about factors that influence AT adoption practices (e.g., misuse of accessible infrastructure, issues with replicating existing commercial ATs), challenges using ATs in social interactions (e.g., Chinese stigma), and misperceptions about ATs (e.g., ATs should overcome inaccessible social infrastructures). Informed by the findings, we derive a set of design considerations to bridge the existing gaps in AT design (e.g., manual vs. electronic ATs) and to improve ATs' social acceptability in China., Comment: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (CHI '21)

Significant advances in video compression system have been made in the past several decades to satisfy the nearly exponential growth of Internet-scale video traffic. From the application perspective, we have identified three major functional blocks including pre-processing, coding, and post-processing, that have been continuously investigated to maximize the end-user quality of experience (QoE) under a limited bit rate budget. Recently, artificial intelligence (AI) powered techniques have shown great potential to further increase the efficiency of the aforementioned functional blocks, both individually and jointly. In this article, we review extensively recent technical advances in video compression system, with an emphasis on deep neural network (DNN)-based approaches; and then present three comprehensive case studies. On pre-processing, we show a switchable texture-based video coding example that leverages DNN-based scene understanding to extract semantic areas for the improvement of subsequent video coder. On coding, we present an end-to-end neural video coding framework that takes advantage of the stacked DNNs to efficiently and compactly code input raw videos via fully data-driven learning. On post-processing, we demonstrate two neural adaptive filters to respectively facilitate the in-loop and post filtering for the enhancement of compressed frames. Finally, a companion website hosting the contents developed in this work can be accessed publicly at https://purdueviper.github.io/dnn-coding/.

Numerical simulations of plasma flow induced by dielectric barrier discharge plasma actuators (DBD-PA) are conducted with two different body-force models: Suzen-Huang (S-H) model and drift-diffusion (D-D) model. The induced flow generated in quiescent air over a flat plate in continuous actuation and the PA-based flow control effect with burst actuation in separated flow over NACA0015 is studied. In the comparative study, the body-force field and the induced velocity field are firstly investigated in the quiescent field to see the spatial difference and the temporal difference in a single discharge cycle. The D-D body force is computed with flush-mounted and bulge configuration of the exposed electrode, which is operated at the peak-to-peak AC voltage of 7kV and 10kV. The D-D models generate momentarily higher body force in the positive-going phase of the AC power, but activate a smaller flow region than the S-H model with Dc = 0.0117, which is given by the experiment beforehand at 7kV. The local induced velocity of the D-D bulge case at 7kV measured in the downstream flow has the best agreement with the experimental result. The maximum wall-parallel induced velocity in the S-H case with Dc = 0.0117 is consistent with that in the experiment, however, the local induced velocity is relatively high with different flow structures. In the post-stall flow over the airfoil at the angle of attack of 12 degrees and Reynolds number of 63000, the D-D bulge model at 7kV has approximately the same effect of leading-edge suction enhancement and reattachment promotion as the S-H model with Dc = 0.16, which was previously proved to be sufficiently high to achieve the control performance., Comment: 16 pages, 15 figures, withdrawn from the conference proceedings of 2020 AIAA AVIATION Forum, to be published in Physics of Fluids

Current datasets for video-based person re-identification (re-ID) do not include structural knowledge in form of human pose annotations for the persons of interest. Nonetheless, pose information is very helpful to disentangle useful feature information from background or occlusion noise. Especially real-world scenarios, such as surveillance, contain a lot of occlusions in human crowds or by obstacles. On the other hand, video-based person re-ID can benefit other tasks such as multi-person pose tracking in terms of robust feature matching. For that reason, we present PoseTrackReID, a large-scale dataset for multi-person pose tracking and video-based person re-ID. With PoseTrackReID, we want to bridge the gap between person re-ID and multi-person pose tracking. Additionally, this dataset provides a good benchmark for current state-of-the-art methods on multi-frame person re-ID.

A key problem in computational sustainability is to understand the distribution of species across landscapes over time. This question gives rise to challenging large-scale prediction problems since (i) hundreds of species have to be simultaneously modeled and (ii) the survey data are usually inflated with zeros due to the absence of species for a large number of sites. The problem of tackling both issues simultaneously, which we refer to as the zero-inflated multi-target regression problem, has not been addressed by previous methods in statistics and machine learning. In this paper, we propose a novel deep model for the zero-inflated multi-target regression problem. To this end, we first model the joint distribution of multiple response variables as a multivariate probit model and then couple the positive outcomes with a multivariate log-normal distribution. By penalizing the difference between the two distributions' covariance matrices, a link between both distributions is established. The whole model is cast as an end-to-end learning framework and we provide an efficient learning algorithm for our model that can be fully implemented on GPUs. We show that our model outperforms the existing state-of-the-art baselines on two challenging real-world species distribution datasets concerning bird and fish populations., Comment: Accepted by IJCAI 2020

Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e.g., image classification, natural language processing, etc. Despite the good performance, the huge number of parameters in DNNs brings challenges to efficient training of DNNs and also their deployment in low-end devices with limited computing resources. In this paper, we explore the correlations in the weight matrices, and approximate the weight matrices with the low-rank block-term tensors. We name the new corresponding structure as block-term tensor layers (BT-layers), which can be easily adapted to neural network models, such as CNNs and RNNs. In particular, the inputs and the outputs in BT-layers are reshaped into low-dimensional high-order tensors with a similar or improved representation power. Sufficient experiments have demonstrated that BT-layers in CNNs and RNNs can achieve a very large compression ratio on the number of parameters while preserving or improving the representation power of the original DNNs., Comment: 12 pages, 15 figures

Non-Volatile Main Memories (NVMMs) have recently emerged as promising technologies for future memory systems. Generally, NVMMs have many desirable properties such as high density, byte-addressability, non-volatility, low cost, and energy efficiency, at the expense of high write latency, high write power consumption and limited write endurance. NVMMs have become a competitive alternative of Dynamic Random Access Memory (DRAM), and will fundamentally change the landscape of memory systems. They bring many research opportunities as well as challenges on system architectural designs, memory management in operating systems (OSes), and programming models for hybrid memory systems. In this article, we first revisit the landscape of emerging NVMM technologies, and then survey the state-of-the-art studies of NVMM technologies. We classify those studies with a taxonomy according to different dimensions such as memory architectures, data persistence, performance improvement, energy saving, and wear leveling. Second, to demonstrate the best practices in building NVMM systems, we introduce our recent work of hybrid memory system designs from the dimensions of architectures, systems, and applications. At last, we present our vision of future research directions of NVMMs and shed some light on design challenges and opportunities., Comment: 36 pages, 13 figures