教学课程资源库 更多>>

关键词： Computer science   Ultracold gases   Quantum simulation  

摘要： Image-like data from quantum systems promises to offer greater insight into the physics of correlated quantum matter. However, the traditional framework of condensed matter physics lacks principled approaches for analyzing such data. Machine learning models are a powerful theoretical tool for analyzing image-like data including many-body snapshots from quantum simulators. Recently, they have successfully distinguished between simulated snapshots that are indistinguishable from one and two point correlation functions. Thus far, the complexity of these models has inhibited new physical insights from such approaches. Here, we develop a set of nonlinearities for use in a neural network architecture that discovers features in the data which are directly interpretable in terms of physical observables. Applied to simulated snapshots produced by two candidate theories approximating the doped Fermi-Hubbard model, we uncover that the key distinguishing features are fourth-order spin-charge correlators. Our approach lends itself well to the construction of simple, versatile, end-to-end interpretable architectures, thus paving the way for new physical insights from machine learning studies of experimental and numerical data. Physical principles underlying machine learning analysis of quantum gas microscopy data are not well understood. Here the authors develop a neural network based approach to classify image data in terms of multi-site correlation functions and reveal the role of fourth-order correlations in the Fermi-Hubbard model.

关键词： Training   Knowledge engineering   Law   History   Geology   Veins   Stress  

摘要： Gentlemen, I feel that we may look upon this first meeting of the newly-formed Students' Section of the South African Institute of Electrical Engineers as an auspicious occasion.

关键词： Computer science   Complex networks  

摘要： Network embedding is a general-purpose machine learning technique that encodes network structure in vector spaces with tunable dimension. Choosing an appropriate embedding dimension - small enough to be efficient and large enough to be effective - is challenging but necessary to generate embeddings applicable to a multitude of tasks. Existing strategies for the selection of the embedding dimension rely on performance maximization in downstream tasks. Here, we propose a principled method such that all structural information of a network is parsimoniously encoded. The method is validated on various embedding algorithms and a large corpus of real-world networks. The embedding dimension selected by our method in real-world networks suggest that efficient encoding in low-dimensional spaces is usually possible. Network embedding is a machine learning technique for construction of low-dimensional representations of large networks. Gu et al. propose a method for the identification of an optimal embedding dimension for the encoding of network structural information inspired by natural language processing.

关键词： Viral infection   Computer science   Nanopores  

摘要： High-throughput, high-accuracy detection of emerging viruses allows for the control of disease outbreaks. Currently, reverse transcription-polymerase chain reaction (RT-PCR) is currently the most-widely used technology to diagnose the presence of SARS-CoV-2. However, RT-PCR requires the extraction of viral RNA from clinical specimens to obtain high sensitivity. Here, we report a method for detecting novel coronaviruses with high sensitivity by using nanopores together with artificial intelligence, a relatively simple procedure that does not require RNA extraction. Our final platform, which we call the artificially intelligent nanopore, consists of machine learning software on a server, a portable high-speed and high-precision current measuring instrument, and scalable, cost-effective semiconducting nanopore modules. We show that artificially intelligent nanopores are successful in accurately identifying four types of coronaviruses similar in size, HCoV-229E, SARS-CoV, MERS-CoV, and SARS-CoV-2. Detection of SARS-CoV-2 in saliva specimen is achieved with a sensitivity of 90% and specificity of 96% with a 5-minute measurement. Rapid, accurate and specific point-of-care diagnostics can help manage and contain fast-spreading infections. Here, the authors present a nanopore-based system that uses artificial intelligence to discriminate between four coronaviruses in saliva, with little need for sample pre-processing.

关键词： Power demand   Data centers   Correlation   Routing   Optimization   Software   Computer science   Data center network (DCN)   device sleeping   device state transition   link rate adaptation   power-efficient routing   software-defined networking (SDN)  

摘要： The energy consumed by data centers has been growing rapidly in recent years. Among all the major contributors to the power consumption of entire data centers, data center network (DCN) can account for up to 20% of the total power consumption. In this article, we first devise a power-efficient software-defined DCN (PESD-DCN) framework, which can achieve desirable power efficiency, avoid potential link congestion, and reduce frequent device state transition. Then, we formulate the optimization problem of maximizing the radio full-utilized devices to all devices. To solve it, we propose correlation-aware flow routing (CFR) algorithm, which leverages correlation-aware flow consolidation (CFC) technique to improve energy efficiency, avoid the potential link congestion, and reduce frequent device state transition. Moreover, to further improve the DCN energy efficiency, we propose flow rerouting, link rate adaptation, and device sleeping (FLD) algorithm. Finally, simulation results demonstrate that PESD-DCN can achieve a good performance. More specifically, in comparison to the other baseline algorithms, PESD-DCN can achieve up to 79.19% energy efficiency, 67.1% decrease in switch state transition (SST), and 55.4% decrease in link state transition (LST).

关键词： Electrical and electronic engineering   Computer science   Glaucoma  

摘要： Glaucoma is the leading cause of irreversible blindness in the world, affecting over 70 million people. The cumbersome Standard Automated Perimetry (SAP) test is most frequently used to detect visual loss due to glaucoma. Due to the SAP test's innate difficulty and its high test-retest variability, we propose the RetiNerveNet, a deep convolutional recursive neural network for obtaining estimates of the SAP visual field. RetiNerveNet uses information from the more objective Spectral-Domain Optical Coherence Tomography (SDOCT). RetiNerveNet attempts to trace-back the arcuate convergence of the retinal nerve fibers, starting from the Retinal Nerve Fiber Layer (RNFL) thickness around the optic disc, to estimate individual age-corrected 24-2 SAP values. Recursive passes through the proposed network sequentially yield estimates of the visual locations progressively farther from the optic disc. While all the methods used for our experiments exhibit lower performance for the advanced disease group (possibly due to the "floor effect" for the SDOCT test), the proposed network is observed to be more accurate than all the baselines for estimating the individual visual field values. We further augment the proposed network to additionally predict the SAP Mean Deviation values and also facilitate the assignment of higher weightage to the underrepresented groups in the data. We then study the resulting performance trade-offs of the RetiNerveNet on the early, moderate and severe disease groups.

关键词： Experimental models of disease   Information technology   Computer science  

摘要： Realistic image generation is valuable in dental medicine, but still challenging for generative adversarial networks (GANs), which require large amounts of data to overcome the training instability. Thus, we generated lateral cephalogram X-ray images using a deep-learning-based progressive growing GAN (PGGAN). The quality of generated images was evaluated by three methods. First, signal-to-noise ratios of real/synthesized images, evaluated at the posterior arch region of the first cervical vertebra, showed no statistically significant difference (t-test, p=0.211). Second, the results of an image Turing test, conducted by non-orthodontists and orthodontists for 100 randomly chosen images, indicated that they had difficulty in distinguishing whether the image was real or synthesized. Third, cephalometric tracing with 42 landmark points detection, performed on real and synthesized images by two expert orthodontists, showed consistency with mean difference of 2.08 +/- 1.02 mm. Furthermore, convolutional neural network-based classification tasks were used to classify skeletal patterns using a real dataset with class imbalance and a dataset balanced with synthesized images. The classification accuracy for the latter case was increased by 1.5%/3.3% at internal/external test sets, respectively. Thus, the cephalometric images generated by PGGAN are sufficiently realistic and have potential to application in various fields of dental medicine.

关键词： Publishing   Computer science   Research data   Ethics  

摘要： The nonsensical computer-generated articles, spotted years after the problem was first seen, could lead to a wave of retractions.

关键词： Computer science   Industry   Information technology   Materials science  

摘要： Artificial intelligence can help the electronics industry to speed up chip design. But the gains must be shared equitably. [Figure not available: see fulltext.]. © 2021, Nature.

关键词： Computer science education   Curriculum   Higher education   Career goals   Diversity   Retention  

摘要： Purpose - As the field of Computer Science (CS) continues to diversify and expand, the need for undergraduates to explore career possibilities and develop personalized study paths has never been greater. This reality presents a challenge for CS departments. How do the students striving to become competent professionals in an ever-changing field of study? How do they do this efficiently and effectively? This study addresses such questions by introducing RadGrad, an online application combining features of social networks, degree planners and serious games. Design/methodology/approach - RadGrad application is designed to promote participation in extracurricular activities, value real-world experience and provide guidance for students planning their degrees. What follows is an exploration of how the application was designed, along with an analysis of how students used it in its first year. Findings - Findings suggest RadGrad helped students to participate in relevant community activities and take an active role in planning their degrees. Originality/value - The paper describes the features of the application, introducing how the concept of Innovation, Competence and Experience (ICE) scores - rather than a GPAs - were used to motivate undergraduates to participate in extracurricular activities. Initial results suggest RadGrad and the concept ICE scores can be applied to any field where students are encouraged to gain real-world experience as part of their degree program. Lessons learned and future directions are discussed.