skip to main content

Title: Multitribe evolutionary search for stable Cu–Pd–Ag nanoparticles using neural network models
We present an approach based on two bio-inspired algorithms to accelerate the identification of nanoparticle ground states. We show that a symbiotic co-evolution of nanoclusters across a range of sizes improves the search efficiency considerably, while a neural network constructed with a recently introduced stratified training scheme delivers an accurate description of interactions in multielement systems. The method's performance has been examined in extensive searches for stable elemental (30–80 atoms), binary (50, 55, and 80 atoms), and ternary (50, 55, and 80 atoms) Cu–Pd–Ag clusters. The best candidate structures identified with the neural network model have consistently lower energy at the density functional theory level compared with those found with traditional interatomic potentials.
; ; ;
Award ID(s):
Publication Date:
Journal Name:
Physical Chemistry Chemical Physics
Page Range or eLocation-ID:
8729 to 8742
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Background Numerous cardiometabolic factors may underlie risk of hearing loss. Modifiable risk factors such as non-optimal blood pressure (BP) are of interest. Purpose To investigate early auditory evoked potentials (AEPs) in persons with nonoptimal BP. Research Design A cross-sectional nonexperimental study was performed. Study Sample Fifty-two adults (18–55 years) served as subjects. Individuals were classified as having optimal (systolic [S] BP < 120 and diastolic [D] BP < 80 mm Hg, n = 25) or non-optimal BP (SBP ≥=120 or DBP ≥=80 mm Hg or antihypertensive use, n = 27). Thirteen subjects had hypertension (HTN) (SBP ≥130 or DBP ≥80 mm Hg or use of antihypertensives). Data Collection and Analysis Behavioral thresholds from 0.25 to 16 kHz were collected. Threshold auditory brain stem responses (ABRs) were recorded using rarefaction clicks (17.7/second) from 80 dB nHL to wave V threshold. Electrocochleograms were obtained with 90 dB nHL 7.1/second alternating clicks and assessed for summating and compound action potentials (APs). Outcomes were compared via independent samples t tests. Linear mixed effects models for behavioral thresholds and ABR wave latencies were constructed to account for potential confounders. Results Wave I and III latencies were comparable between optimal and non-optimal BP groups. Wave I was prolonged in hypertensive versus optimal BP subjects at stimulus level 70 dB nHL (p = 0.016). ABR wave V latencies weremore »prolonged in non-optimal BP at stimulus level 80 dB nHL (p = 0.048) and in HTN at levels of 80, 50, and 30 dB nHL (all p < 0.050). DBP was significantly correlated with wave V latency (r = 0.295; p = 0.039). No differences in ABR amplitudes were observed between optimal and non-optimal BP subjects. Electrocochleographic study showed statistically comparable action and summating potential amplitudes between optimal and non-optimal BP subjects. AP latencies were also similar between the groups. Analysis using a set baseline amplitude of 0 μV showed that hypertensive subjects had higher summating (p = 0.038) and AP (p = 0.047) amplitudes versus optimal BP subjects; AP latencies were comparable. Conclusion Elevated BP and more specifically, HTN was associated with subtle AEP abnormalities. This study provides preliminary evidence that nonoptimal BP, and more specifically HTN, may be related to auditory neural dysfunction; larger confirmatory studies are warranted.« less
  2. For decades, atomistic modeling has played a crucial role in predicting the behavior of materials in numerous fields ranging from nanotechnology to drug discovery. The most accurate methods in this domain are rooted in first-principles quantum mechanical calculations such as density functional theory (DFT). Because these methods have remained computationally prohibitive, practitioners have traditionally focused on defining physically motivated closed-form expressions known as empirical interatomic potentials (EIPs) that approximately model the interactions between atoms in materials. In recent years, neural network (NN)-based potentials trained on quantum mechanical (DFT-labeled) data have emerged as a more accurate alternative to conventional EIPs. However, the generalizability of these models relies heavily on the amount of labeled training data, which is often still insufficient to generate models suitable for general-purpose applications. In this paper, we propose two generic strategies that take advantage of unlabeled training instances to inject domain knowledge from conventional EIPs to NNs in order to increase their generalizability. The first strategy, based on weakly supervised learning, trains an auxiliary classifier on EIPs and selects the best-performing EIP to generate energies to supplement the ground-truth DFT energies in training the NN. The second strategy, based on transfer learning, first pretrains the NN onmore »a large set of easily obtainable EIP energies, and then fine-tunes it on ground-truth DFT energies. Experimental results on three benchmark datasets demonstrate that the first strategy improves baseline NN performance by 5% to 51% while the second improves baseline performance by up to 55%. Combining them further boosts performance.« less
  3. ABSTRACT We present the results of a proof-of-concept experiment that demonstrates that deep learning can successfully be used for production-scale classification of compact star clusters detected in Hubble Space Telescope(HST) ultraviolet-optical imaging of nearby spiral galaxies ($D\lesssim 20\, \textrm{Mpc}$) in the Physics at High Angular Resolution in Nearby GalaxieS (PHANGS)–HST survey. Given the relatively small nature of existing, human-labelled star cluster samples, we transfer the knowledge of state-of-the-art neural network models for real-object recognition to classify star clusters candidates into four morphological classes. We perform a series of experiments to determine the dependence of classification performance on neural network architecture (ResNet18 and VGG19-BN), training data sets curated by either a single expert or three astronomers, and the size of the images used for training. We find that the overall classification accuracies are not significantly affected by these choices. The networks are used to classify star cluster candidates in the PHANGS–HST galaxy NGC 1559, which was not included in the training samples. The resulting prediction accuracies are 70 per cent, 40 per cent, 40–50 per cent, and 50–70 per cent for class 1, 2, 3 star clusters, and class 4 non-clusters, respectively. This performance is competitive with consistency achieved in previously published human and automated quantitative classification of starmore »cluster candidate samples (70–80 per cent, 40–50 per cent, 40–50 per cent, and 60–70 per cent). The methods introduced herein lay the foundations to automate classification for star clusters at scale, and exhibit the need to prepare a standardized data set of human-labelled star cluster classifications, agreed upon by a full range of experts in the field, to further improve the performance of the networks introduced in this study.« less
  4. Over 8 million users rely on the Tor network each day to protect their anonymity online. Unfortunately, Tor has been shown to be vulnerable to the website fingerprinting attack, which allows an attacker to deduce the website a user is visiting based on patterns in their traffic. The state-of-the-art attacks leverage deep learning to achieve high classification accuracy using raw packet information. Work thus far, however, has examined only one type of media delivered over the Tor network: web pages, and mostly just home pages of sites. In this work, we instead investigate the fingerprintability of video content served over Tor. We collected a large new dataset of network traces for 50 YouTube videos of similar length. Our preliminary experiments utilizing a convolutional neural network model proposed in prior works has yielded promising classification results, achieving up to 55% accuracy. This shows the potential to unmask the individual videos that users are viewing over Tor, creating further privacy challenges to consider when defending against website fingerprinting attacks.
  5. ABSTRACT When completed, the PHANGS–HST project will provide a census of roughly 50 000 compact star clusters and associations, as well as human morphological classifications for roughly 20 000 of those objects. These large numbers motivated the development of a more objective and repeatable method to help perform source classifications. In this paper, we consider the results for five PHANGS–HST galaxies (NGC 628, NGC 1433, NGC 1566, NGC 3351, NGC 3627) using classifications from two convolutional neural network architectures (RESNET and VGG) trained using deep transfer learning techniques. The results are compared to classifications performed by humans. The primary result is that the neural network classifications are comparable in quality to the human classifications with typical agreement around 70 to 80 per cent for Class 1 clusters (symmetric, centrally concentrated) and 40 to 70 per cent for Class 2 clusters (asymmetric, centrally concentrated). If Class 1 and 2 are considered together the agreement is 82 ± 3 per cent. Dependencies on magnitudes, crowding, and background surface brightness are examined. A detailed description of the criteria and methodology used for the human classifications is included along with an examination of systematic differences between PHANGS–HST and LEGUS. The distribution of data points in a colour–colour diagram is used as a ‘figure ofmore »merit’ to further test the relative performances of the different methods. The effects on science results (e.g. determinations of mass and age functions) of using different cluster classification methods are examined and found to be minimal.« less