Article
|
Open Access
Featured
-
-
Article
| Open AccessAutomated detection and segmentation of non-small cell lung cancer computed tomography images
Correct interpretation of computer tomography (CT) scans is important for the correct assessment of a patient’s disease but can be subjective and timely. Here, the authors develop a system that can automatically segment the non-small cell lung cancer on CT images of patients and show in an in silico trial that the method was faster and more reproducible than clinicians.
- Sergey P. Primakov
- , Abdalla Ibrahim
- & Philippe Lambin
-
Article
| Open AccessA framework for the general design and computation of hybrid neural networks
Hybrid neural networks combine advantages of spiking and artificial neural networks in the context of computing and biological motivation. The authors propose a design framework with hybrid units for improved flexibility and efficiency of hybrid neural networks, and modulation of hybrid information flows.
- Rong Zhao
- , Zheyu Yang
- & Luping Shi
-
Article
| Open AccessAccelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties
Screening polymer electrolytes for batteries is extremely expensive due to the complex structures and slow dynamics. Here the authors develop a machine learning scheme to accelerate the screening and explore a space much larger than past studies.
- Tian Xie
- , Arthur France-Lanord
- & Jeffrey C. Grossman
-
Article
| Open AccessLearning emergent partial differential equations in a learned emergent space
Machine learning tools allow to extract dynamical systems from data, however this problem remains challenging for networks and systems of interacting agents. The authors introduce an approach to learn a predictive model for the dynamics of coupled agents in the form of partial differential equations using emergent spatial embeddings.
- Felix P. Kemeth
- , Tom Bertalan
- & Ioannis G. Kevrekidis
-
Article
| Open AccessParamagnetic encoding of molecules
Molecules offer enormous capacity for information storage. Here, the authors show that information can be encoded into molecules with sequences of paramagnetic lanthanide ions, and decoded using nuclear magnetic resonance spectroscopy.
- Jan Kretschmer
- , Tomáš David
- & Miloslav Polasek
-
Article
| Open AccessDeciphering quantum fingerprints in electric conductance
Scattering of electrons from defects and boundaries in mesoscopic samples is encoded in quantum interference patterns of magneto-conductance, but these patterns are difficult to interpret. Here the authors use machine learning to reconstruct electron wavefunction intensities and sample geometry from magneto-conductance data.
- Shunsuke Daimon
- , Kakeru Tsunekawa
- & Eiji Saitoh
-
Article
| Open AccessMulti-scale turbulence simulation suggesting improvement of electron heated plasma confinement
Understanding the transport of the particles and fuel in the fusion plasma is fundamentally important. Here the authors report a cross-link interaction between electron- and ion-scale turbulences in plasma in terms of trapped electron mode and electron temperature gradient modes and their implication to fusion plasma.
- Shinya Maeyama
- , Tomo-Hiko Watanabe
- & Akihiro Ishizawa
-
Article
| Open AccessUntangling the changing impact of non-pharmaceutical interventions and vaccination on European COVID-19 trajectories
Non-pharmaceutical interventions (NPIs) and COVID-19 vaccination have been implemented concurrently, making their relative effects difficult to measure. Here, the authors show that effects of NPIs reduced as vaccine coverage increased, but that NPIs could still be important in the context of more transmissible variants.
- Yong Ge
- , Wen-Bin Zhang
- & Shengjie Lai
-
Article
| Open AccessTowards artificial general intelligence via a multimodal foundation model
Artificial intelligence approaches inspired by human cognitive function have usually single learned ability. The authors propose a multimodal foundation model that demonstrates the cross-domain learning and adaptation for broad range of downstream cognitive tasks.
- Nanyi Fei
- , Zhiwu Lu
- & Ji-Rong Wen
-
Article
| Open AccessRelative, local and global dimension in complex networks
Defining the dimension in bounded, inhomogeneous or discrete physical systems may be challenging. The authors introduce here a dynamics-based notion of dimension by analysing diffusive processes in space, relevant for non-ideal physical systems and networks.
- Robert Peach
- , Alexis Arnaudon
- & Mauricio Barahona
-
Article
| Open AccessFull reconstruction of simplicial complexes from binary contagion and Ising data
Data-driven recovery of topology is challenging for networks beyond pairwise interactions. The authors propose a framework to reconstruct complex networks with higher-order interactions from time series, focusing on networks with 2-simplexes where social contagion and Ising dynamics generate binary data.
- Huan Wang
- , Chuang Ma
- & Hai-Feng Zhang
-
Article
| Open AccessHomogeneous solution assembled Turing structures with near zero strain semi-coherence interface
Turing structures emerge in reaction-diffusion processes far from thermodynamic equilibrium involving chemicals with different diffusion coefficients in classic Turing systems. Here, authors show that a Turing structure with near zero strain semi-coherence interfaces can be constructed in homogeneous solutions.
- Yuanming Zhang
- , Ningsi Zhang
- & Zhigang Zou
-
Matters Arising
| Open AccessComments on identifying causal relationships in nonlinear dynamical systems via empirical mode decomposition
- Chun-Wei Chang
- , Stephan B. Munch
- & Chih-hao Hsieh
-
Matters Arising
| Open AccessReply To: Comments on identifying causal relationships in nonlinear dynamical systems via empirical mode decomposition
- Albert C. Yang
- , Chung-Kang Peng
- & Norden E. Huang
-
Article
| Open AccessZeolite-confined subnanometric PtSn mimicking mortise-and-tenon joinery for catalytic propane dehydrogenation
The atomic structure of heterogeneous catalysts is usually a blackbox. Here the authors demonstrate large-scale machine learning atomic simulations help to resolve the catalyst structure and reaction mechanism of encapsulated PtSnOx clusters in zeolite that feature a mortise-and-tenon joinery structure and the superior activity towards propane dehydrogenation.
- Sicong Ma
- & Zhi-Pan Liu
-
Article
| Open AccessMedial packing and elastic asymmetry stabilize the double-gyroid in block copolymers
Double-gyroid networks assemble in diverse soft materials, yet the molecular packing that underlies their complex structure remains obscure. Here, authors advance a theory that resolves a long-standing puzzle about their formation in block copolymers.
- Abhiram Reddy
- , Michael S. Dimitriyev
- & Gregory M. Grason
-
Article
| Open AccessE(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials
An E(3)-equivariant deep learning interatomic potential is introduced for accelerating molecular dynamics simulations. The method obtains state-of-the-art accuracy, can faithfully describe dynamics of complex systems with remarkable sample efficiency.
- Simon Batzner
- , Albert Musaelian
- & Boris Kozinsky
-
Article
| Open AccessData-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation
Accurate capacity estimation is crucial for lithium-ion batteries' reliable and safe operation. Here, the authors propose an approach exploiting features from the relaxation voltage curve for battery capacity estimation without requiring other previous cycling information.
- Jiangong Zhu
- , Yixiu Wang
- & Helmut Ehrenberg
-
Article
| Open AccessAutomated exploitation of the big configuration space of large adsorbates on transition metals reveals chemistry feasibility
The discovery of heterogeneous catalysts for large molecule conversion has been lagging due to the combinatorial inventory of intermediates. Here, the author presents an automated framework to explore the chemical space of reaction intermediates.
- Geun Ho Gu
- , Miriam Lee
- & Dionisios G. Vlachos
-
Article
| Open AccessNanosecond optical switching and control system for data center networks
Several challenges still impede the deployment of optical switches in data centers. The authors report an optical switching and control system to synergistically overcome these challenges and provide enhanced performance for data center applications.
- Xuwei Xue
- & Nicola Calabretta
-
Article
| Open AccessThe neural coding framework for learning generative models
Brain-inspired neural generative models can be designed to learn complex probability distributions from data. Here the authors propose a neural generative computational framework, inspired by the theory of predictive processing in the brain, that facilitates parallel computing for complex tasks.
- Alexander Ororbia
- & Daniel Kifer
-
Article
| Open AccessLocal structure-function relationships in human brain networks across the lifespan
How regional anatomy shapes function is not well understood. Here, the authors evaluate the performance of 40 communication models in predicting functional connectivity, and find regional heterogeneity in terms of fit and optimal model, and that regional coupling varies over the human lifespan.
- Farnaz Zamani Esfahlani
- , Joshua Faskowitz
- & Richard F. Betzel
-
Article
| Open AccessDeep learning enhanced Rydberg multifrequency microwave recognition
Rydberg atoms are sensitive to microwave signals and hence can be used to detect them. Here the authors demonstrate a Rydberg receiver enhanced by deep learning, Rydberg atoms acting as antennae, to receive, extract, and decode the multi-frequency microwave signal effectively.
- Zong-Kai Liu
- , Li-Hua Zhang
- & Bao-Sen Shi
-
Article
| Open AccessUsing high-resolution contact networks to evaluate SARS-CoV-2 transmission and control in large-scale multi-day events
Here, the authors simulate COVID-19 outbreaks on an empirical contact network derived from digital contact data collected on cruise ships. They model impacts of different control measures and find that combinations of measures, particularly vaccination and rapid antigen testing, are important for mitigating outbreaks.
- Rachael Pung
- , Josh A. Firth
- & Adam J. Kucharski
-
Article
| Open AccessIntroducing principles of synaptic integration in the optimization of deep neural networks
Tasks involving continual learning and adaptation to real-time scenarios remain challenging for artificial neural networks in contrast to real brain. The authors propose here a brain-inspired optimizer based on mechanisms of synaptic integration and strength regulation for improved performance of both artificial and spiking neural networks.
- Giorgia Dellaferrera
- , Stanisław Woźniak
- & Evangelos Eleftheriou
-
Article
| Open AccessAccurate auto-labeling of chest X-ray images based on quantitative similarity to an explainable AI model
Here the authors develop a method for accurate auto-labelling of CXR images from large public datasets based on quantitative probability-of similarity to an explainable AI model. The labels can be used to fine-tune the original model through iterative re-training.
- Doyun Kim
- , Joowon Chung
- & Synho Do
-
Article
| Open AccessGroup testing via hypergraph factorization applied to COVID-19
This paper proposes HYPER, a method for screening more people using fewer tests by testing pools formed via hypergraph factorization. HYPER is not only efficient but is also simple to implement, flexible, and has maximally balanced pools.
- David Hong
- , Rounak Dey
- & Edgar Dobriban
-
Article
| Open AccessImmunosuppressive niche engineering at the onset of human colorectal cancer
Integration of mathematical modeling, ecological analyses of patient biopsies, and neoantigen heterogeneity suggests recruitment of immunosuppressive cells is key to initializing transformation from adenoma to carcinoma in human colorectal cancer.
- Chandler D. Gatenbee
- , Ann-Marie Baker
- & Alexander R. A. Anderson
-
Article
| Open AccessThe world-wide waste web
The 2001–2019 web of international waste trade is investigated, allowing the identification of countries at threat of improper handling and disposal of waste. Chemical tracers are used to identify the environmental impact of waste in these countries.
- Johann H. Martínez
- , Sergi Romero
- & Ernesto Estrada
-
Article
| Open AccessDynamics of ranking
Ranking lists are relevant to various areas of nature and society, however their evolution with the elements changing rank in time remained unexplored. The authors uncover a mechanism of ranking dynamics induced by the flux governing the arrival of new elements in the list, for improved predictability of ranking models.
- Gerardo Iñiguez
- , Carlos Pineda
- & Albert-László Barabási
-
Article
| Open AccessRotating neurons for all-analog implementation of cyclic reservoir computing
Reservoir computing has demonstrated high-level performance, however efficient hardware implementations demand an architecture with minimum system complexity. The authors propose a rotating neuron-based architecture for physically implementing all-analog resource efficient reservoir computing system.
- Xiangpeng Liang
- , Yanan Zhong
- & Huaqiang Wu
-
Article
| Open AccessScientific multi-agent reinforcement learning for wall-models of turbulent flows
Simulations of turbulent flows are relevant for aerodynamic and weather modeling, however challenging to capture flow dynamics in the near wall region. To solve this problem, the authors propose a multi-agent reinforcement learning approach to discover wall models for large-eddy simulations.
- H. Jane Bae
- & Petros Koumoutsakos
-
Article
| Open AccessAgent-based modelling of reactive vaccination of workplaces and schools against COVID-19
The authors use an agent-based model to investigate the potential of reactive vaccination strategies for COVID-19 outbreak mitigation. They find that distributing vaccines in schools and workplaces where cases are detected is more impactful than non-reactive strategies in a wide range of epidemic scenarios.
- Benjamin Faucher
- , Rania Assab
- & Chiara Poletto
-
Article
| Open AccessPopulation-scale dietary interests during the COVID-19 pandemic
The SARS-CoV-2 virus has altered people’s lives around the world, not only through the disease it causes, but also through unprecedented restrictions. Here the authors document population-wide shifts in dietary interests in 18 countries in 2020, as revealed through time series of Google search volumes.
- Kristina Gligorić
- , Arnaud Chiolero
- & Robert West
-
Perspective
| Open AccessEmbodied neuromorphic intelligence
A grand challenge in robotics is realising intelligent agents capable of autonomous interaction with the environment. In this Perspective, the authors discuss the potential, challenges and future direction of research aimed at demonstrating embodied intelligent robotics via neuromorphic technology.
- Chiara Bartolozzi
- , Giacomo Indiveri
- & Elisa Donati
-
Article
| Open AccessForecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations
Deep learning has an increasing impact to assist research. Here, authors show that a dynamical neural network, trained on a minimal amount of data, can predict the behaviour of spintronic devices with high accuracy and an extremely efficient simulation time.
- Xing Chen
- , Flavio Abreu Araujo
- & Damien Querlioz
-
Article
| Open AccessInverse design of 3d molecular structures with conditional generative neural networks
The targeted discovery of molecules with specific structural and chemical properties is an open challenge in computational chemistry. Here, the authors propose a conditional generative neural network for the inverse design of 3d molecular structures.
- Niklas W. A. Gebauer
- , Michael Gastegger
- & Kristof T. Schütt
-
Article
| Open AccessDensity of states prediction for materials discovery via contrastive learning from probabilistic embeddings
Electrons and phonons give rise to important properties of materials. The machine learning framework Mat2Spec vastly accelerates their computational characterization, enabling discovery of materials for thermoelectrics and solar energy technologies.
- Shufeng Kong
- , Francesco Ricci
- & John M. Gregoire
-
Article
| Open AccessQuantum algorithmic measurement
Applying the language of computational complexity to study real-world experiments requires a rigorous framework. Here, the authors provide such a framework and establish that there can be an exponential savings in resources if an experimentalist can entangle apparatuses with experimental samples.
- Dorit Aharonov
- , Jordan Cotler
- & Xiao-Liang Qi
-
Article
| Open AccessData-driven modeling and prediction of non-linearizable dynamics via spectral submanifolds
Current data-driven modelling techniques perform reliably on linear systems or on those that can be linearized. Cenedese et al. develop a data-based reduced modeling method for non-linear, high-dimensional physical systems. Their models reconstruct and predict the dynamics of the full physical system.
- Mattia Cenedese
- , Joar Axås
- & George Haller
-
Article
| Open AccessDeep learning-based high-accuracy quantitation for lumbar intervertebral disc degeneration from MRI
Globally, as a major public health problem, low back pain has been the leading cause of disability worldwide for the past 30 years. Here, the authors propose a segmentation network and a quantitative method lumbar intervertebral disc degeneration assessment.
- Hua-Dong Zheng
- , Yue-Li Sun
- & Yong-Jun Wang
-
Perspective
| Open AccessPerspectives in machine learning for wildlife conservation
Animal ecologists are increasingly limited by constraints in data processing. Here, Tuia and colleagues discuss how collaboration between ecologists and data scientists can harness machine learning to capitalize on the data generated from technological advances and lead to novel modeling approaches.
- Devis Tuia
- , Benjamin Kellenberger
- & Tanya Berger-Wolf
-
Article
| Open AccessRepresenting individual electronic states for machine learning GW band structures of 2D materials
The study introduces novel methods for representing electronic states as input to machine learning models, which is used to learn high-fidelity band structures of two-dimensional materials from low- fidelity input.
- Nikolaj Rørbæk Knøsgaard
- & Kristian Sommer Thygesen
-
Article
| Open AccessAssessing the impact of SARS-CoV-2 prevention measures in Austrian schools using agent-based simulations and cluster tracing data
How to safely maintain open schools during a pandemic is still controversial. Here, the authors aim to identify those measures that effectively control the spread of SARS-CoV-2 in Austrian schools, with an agent-based mathematical model.
- Jana Lasser
- , Johannes Sorger
- & Peter Klimek
-
Article
| Open AccessInteraction data are identifiable even across long periods of time
Large amounts of interaction data are collected by messaging apps, mobile phone carriers, and social media. Creţu et al. propose a behavioral profiling attack model and show that the stability of people’s interaction networks over time can allow individuals to be re-identified in interaction datasets.
- Ana-Maria Creţu
- , Federico Monti
- & Yves-Alexandre de Montjoye
-
Article
| Open AccessThe shape of memory in temporal networks
The evolution of networks with structure changing in time is dependent on their past states and relevant to diffusion and spreading processes. The authors show that temporal network’s memory is described by multidimensional patterns at a microscopic scale, and cannot be reduced to a scalar quantity.
- Oliver E. Williams
- , Lucas Lacasa
- & Vito Latora
-
Article
| Open AccessSelf-directed online machine learning for topology optimization
Topology optimization, relevant for materials design and engineering, requires solving of challenging high-dimensional problems. The authors introduce a self-directed online learning approach, as embedding of deep learning in optimization methods, that accelerates the training and optimization processes.
- Changyu Deng
- , Yizhou Wang
- & Wei Lu
-
Article
| Open AccessEmergent Sasaki-Einstein geometry and AdS/CFT
It is an outstanding question in quantum gravity how to describe the emergence of classical spacetime geometry from a quantum state. Here, the authors propose a construction in the context of the gauge/gravity correspondence, producing the classical geometry from a quantum state at the boundary of spacetime.
- Robert J. Berman
- , Tristan C. Collins
- & Daniel Persson
-
Review Article
| Open AccessSynthetic DNA applications in information technology
Synthetic DNA is the basis for promising technologies in data storage, barcoding, computing 62 and sercurity. In this review, the authors provide an overview of the field and its future.
- Linda C. Meiser
- , Bichlien H. Nguyen
- & Robert N. Grass