Article
|
Open Access
Featured
-
-
Article
| Open AccessPredicting trends in the quality of state-of-the-art neural networks without access to training or testing data
In many machine learning applications, one uses pre-trained neural networks, having limited access to training and test data. Martin et al. show how to predict trends in the quality of such neural networks without access to this information, relevant for reproducibility, diagnostics, and validation.
- Charles H. Martin
- , Tongsu (Serena) Peng
- & Michael W. Mahoney
-
Article
| Open AccessOne-way dependent clusters and stability of cluster synchronization in directed networks
Mechanisms of cluster formation in networks with directed links differ from those in undirected networks. Lodi et al. propose a method to compute interdependencies among clusters of nodes in directed networks. They show that clusters can be one-way dependent, as found in social and neural networks.
- Matteo Lodi
- , Francesco Sorrentino
- & Marco Storace
-
Article
| Open AccessFast and strong amplifiers of natural selection
Population structure can influence the probability of and time to fixation of new mutants. Here, Tkadlec et al. demonstrate mathematically that structures that increase fixation probability necessarily slow fixation, but also identify amplifying structures with minimal reductions in fixation time.
- Josef Tkadlec
- , Andreas Pavlogiannis
- & Martin A. Nowak
-
Article
| Open AccessContinuous-capture microwave imaging
The authors present a microwave imaging system that can operate in continuous transmit-receive mode. Using an array of transmitters, a single receiver and a reconstruction matrix that correlate random time patterns with the captured signal, they demonstrate real-time imaging and tracking through a wall.
- Fabio C. S. da Silva
- , Anthony B. Kos
- & Archita Hati
-
Article
| Open AccessCorrelator convolutional neural networks as an interpretable architecture for image-like quantum matter 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.
- Cole Miles
- , Annabelle Bohrdt
- & Eun-Ah Kim
-
Article
| Open AccessReconstruction of plant–pollinator networks from observational data
Networks describe the intricate patterns of interaction occurring within ecological systems, but they are unfortunately difficult to construct from data. Here, the authors show how Bayesian statistical techniques can separate structure from noise in networks gathered in observational studies of plant-pollinator systems.
- Jean-Gabriel Young
- , Fernanda S. Valdovinos
- & M. E. J. Newman
-
Article
| Open AccessIn-silico trial of intracranial flow diverters replicates and expands insights from conventional clinical trials
In-silico trials rely on virtual populations and interventions simulated using patient-specific models and may offer a solution to lower costs. Here, the authors present the flow diverter performance assessment in-silico trial, which models the treatment of intracranial aneurysms with a flow-diverting stent.
- Ali Sarrami-Foroushani
- , Toni Lassila
- & Alejandro F. Frangi
-
Matters Arising
| Open AccessInadequate methods undermine a study of malaria, deforestation and trade
- Nikolas Kuschnig
-
Article
| Open AccessPrincipled approach to the selection of the embedding dimension of networks
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.
- Weiwei Gu
- , Aditya Tandon
- & Filippo Radicchi
-
Article
| Open AccessCombining machine learning and nanopore construction creates an artificial intelligence nanopore for coronavirus detection
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.
- Masateru Taniguchi
- , Shohei Minami
- & Kazunori Tomono
-
Article
| Open AccessGeneration of gravity waves from thermal tides in the Venus atmosphere
Gravity waves are observed in Venus atmosphere, but their characteristics are not well-known. Here, the authors show spontaneous generation of gravity waves from the thermal tides in the Venus atmosphere as small-scale gravity waves are resolved in high-resolution general circulation model.
- Norihiko Sugimoto
- , Yukiko Fujisawa
- & Yoshi-Yuki Hayashi
-
Article
| Open AccessIdentification of optimal dosing schedules of dacomitinib and osimertinib for a phase I/II trial in advanced EGFR-mutant non-small cell lung cancer
Osimertinib and dacomitinib are approved as first-line treatment of EGFR-mutant NSCLC but resistance can arise. Here, the authors use a computational model to identify an optimal dosing schedule for osimertinib and dacomitinib combination therapy that was confirmed tolerable and effective in an ongoing phase I clinical trial.
- Kamrine E. Poels
- , Adam J. Schoenfeld
- & Franziska Michor
-
Article
| Open AccessEffect of COVID-19 response policies on walking behavior in US cities
Mobility restrictions implemented to reduce the spread of COVID-19 have significantly impacted walking behavior. In this study, the authors integrated mobility data from mobile devices and area-level data to study the walking patterns of 1.62 million anonymous users in 10 US metropolitan areas.
- Ruth F. Hunter
- , Leandro Garcia
- & Esteban Moro
-
Article
| Open AccessControlling the pandemic during the SARS-CoV-2 vaccination rollout
Despite the consensus that mass vaccination against SARS-CoV-2 will ultimately end the pandemic, it is not clear when and which control measures can be relaxed during the rollout of vaccination programmes. Here, the authors investigate relaxation scenarios using an age-structured transmission model that has been fitted to data for Portugal.
- João Viana
- , Christiaan H. van Dorp
- & Ganna Rozhnova
-
Article
| Open AccessFluctuation spectra of large random dynamical systems reveal hidden structure in ecological networks
Fluctuations in ecosystems and other large dynamical systems are driven by intrinsic and extrinsic noise and contain hidden information which is difficult to extract. Here, the authors derive analytical characterizations of fluctuations in random interacting systems, allowing inference of network properties from time series data.
- Yvonne Krumbeck
- , Qian Yang
- & Tim Rogers
-
Article
| Open AccessAspiration dynamics generate robust predictions in heterogeneous populations
Social interaction outcomes can depend on the type of information individuals possess and how it is used in decision-making. Here, Zhou et al. find that self-evaluation based decision-making rules lead to evolutionary outcomes that are robust to different population structures and ways of self-evaluation.
- Lei Zhou
- , Bin Wu
- & Long Wang
-
Article
| Open AccessRobust learning from noisy, incomplete, high-dimensional experimental data via physically constrained symbolic regression
Reinbold et al. propose a physics-informed data-driven approach that successfully discovers a dynamical model using high-dimensional, noisy and incomplete experimental data describing a weakly turbulent fluid flow. This approach is relevant to other non-equilibrium spatially-extended systems.
- Patrick A. K. Reinbold
- , Logan M. Kageorge
- & Roman O. Grigoriev
-
Article
| Open AccessMasked graph modeling for molecule generation
Generating new sensible molecular structures is a key problem in computer aided drug discovery. Here the authors propose a graph-based molecular generative model that outperforms previously proposed graph-based generative models of molecules and performs comparably to several SMILES-based models.
- Omar Mahmood
- , Elman Mansimov
- & Kyunghyun Cho
-
Article
| Open AccessNetwork isolators inhibit failure spreading in complex networks
A single damage can lead to a complete collapse of supply networks due to a cascading failure mechanism. Kaiser et al. show that by adding new connections network isolators can be created, that can inhibit failure spreading relevant for power grids and water transmission systems.
- Franz Kaiser
- , Vito Latora
- & Dirk Witthaut
-
Article
| Open AccessHealth improvement framework for actionable treatment planning using a surrogate Bayesian model
Clinical decision-making regarding treatments based on personal characteristics leads to effective health improvements. Here, the authors introduce a modeling framework to evaluate the actionability of treatment pathways.
- Kazuki Nakamura
- , Ryosuke Kojima
- & Yasushi Okuno
-
Article
| Open AccessDeep learning the structural determinants of protein biochemical properties by comparing structural ensembles with DiffNets
Comparing and contrasting structural ensembles of different protein variants helps connect specific structural features to a protein’s biochemical properties. Here, the authors propose DiffNets, a self-supervised, deep learning method that streamlines this process.
- Michael D. Ward
- , Maxwell I. Zimmerman
- & Gregory R. Bowman
-
Article
| Open AccessPhase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning
The design and optimization of a metasurface is a computationally- and time-consuming effort. Here, the authors propose a neural network-based algorithm for functional metasurface design, and demonstrate it for some functional metasurfaces.
- Ruichao Zhu
- , Tianshuo Qiu
- & Shaobo Qu
-
Article
| Open AccessEvent generation and statistical sampling for physics with deep generative models and a density information buffer
Here, the authors report buffered-density variational autoencoders for the generation of physical events. This method is computationally less expensive over other traditional methods and beyond accelerating the data generation process, it can help to steer the generation and to detect anomalies.
- Sydney Otten
- , Sascha Caron
- & Rob Verheyen
-
Article
| Open AccessMultiscale influenza forecasting
Influenza forecasting in the United States is challenging and consequential, with the ability to improve the public health response. Here the authors show the performance of the multiscale flu forecasting model, Dante, that won the CDC’s 2018/19 national, regional and state flu forecasting challenges.
- Dave Osthus
- & Kelly R. Moran
-
Article
| Open AccessSpectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks
Canatar et al. propose a predictive theory of generalization in kernel regression applicable to real data. This theory explains various generalization phenomena observed in wide neural networks, which admit a kernel limit and generalize well despite being overparameterized.
- Abdulkadir Canatar
- , Blake Bordelon
- & Cengiz Pehlevan
-
Article
| Open AccessModeling regulatory network topology improves genome-wide analyses of complex human traits
Gene regulatory networks are a useful means of inferring functional interactions from large-scale genomic data. Here, the authors develop a Bayesian framework integrating GWAS summary statistics with gene regulatory networks to identify genetic enrichments and associations simultaneously.
- Xiang Zhu
- , Zhana Duren
- & Wing Hung Wong
-
Article
| Open AccessThe epidemicity index of recurrent SARS-CoV-2 infections
Several prognostic indices are available to predict the long-term fate of emerging infectious diseases and the effect of their containment measures, including a variety of reproduction numbers. Here, the authors introduce the epidemicity index, a complementary index to evaluate the potential for transient increases of SARS-Cov-2 epidemics.
- Lorenzo Mari
- , Renato Casagrandi
- & Marino Gatto
-
Article
| Open AccessPower of data in quantum machine learning
Expectations for quantum machine learning are high, but there is currently a lack of rigorous results on which scenarios would actually exhibit a quantum advantage. Here, the authors show how to tell, for a given dataset, whether a quantum model would give any prediction advantage over a classical one.
- Hsin-Yuan Huang
- , Michael Broughton
- & Jarrod R. McClean
-
Article
| Open AccessNeural network aided approximation and parameter inference of non-Markovian models of gene expression
Cells are complex systems that make decisions biologists struggle to understand. Here, the authors use neural networks to approximate the solution of mathematical models that capture the history and randomness of biochemical processes in order to understand the principles of transcription control.
- Qingchao Jiang
- , Xiaoming Fu
- & Ramon Grima
-
Article
| Open AccessInferring experimental procedures from text-based representations of chemical reactions
In organic chemistry, synthetic routes for new molecules are often specified in terms of reacting molecules only. The current work reports an artificial intelligence model to predict the full sequence of experimental operations for an arbitrary chemical equation.
- Alain C. Vaucher
- , Philippe Schwaller
- & Teodoro Laino
-
Article
| Open AccessSynaptic metaplasticity in binarized neural networks
Deep neural networks usually rapidly forget the previously learned tasks while training new ones. Laborieux et al. propose a method for training binarized neural networks inspired by neuronal metaplasticity that allows to avoid catastrophic forgetting and is relevant for neuromorphic applications.
- Axel Laborieux
- , Maxence Ernoult
- & Damien Querlioz
-
Article
| Open AccessRobust high-dimensional memory-augmented neural networks
The implementation of memory-augmented neural networks using conventional computer architectures is challenging due to a large number of read and write operations. Here, Karunaratne, Schmuck et al. propose an architecture that enables analog in-memory computing on high-dimensional vectors at accuracy matching 32-bit software equivalent.
- Geethan Karunaratne
- , Manuel Schmuck
- & Abbas Rahimi
-
Article
| Open AccessNeural network based 3D tracking with a graphene transparent focal stack imaging system
Transparent photodetectors based on graphene stacked vertically along the optical axis have shown promising potential for light field reconstruction. Here, the authors develop transparent photodetector arrays and implement a neural network for real-time 3D optical imaging and object tracking.
- Dehui Zhang
- , Zhen Xu
- & Theodore B. Norris
-
Article
| Open AccessReaction-diffusion in a growing 3D domain of skin scales generates a discrete cellular automaton
The adult ocellated lizard skin colour pattern is effectively generated by a stochastic cellular automaton (CA) of skin scales. Here authors use reaction diffusion (RD) numerical simulations in 3D on realistic lizard skin geometries and demonstrate that skin thickness variation on its own is sufficient to cause scale-by-scale coloration and CA dynamics during RD patterning.
- Anamarija Fofonjka
- & Michel C. Milinkovitch
-
Article
| Open AccessGenomic architecture and prediction of censored time-to-event phenotypes with a Bayesian genome-wide analysis
Few genome-wide association studies have explored the genetic architecture of age-of-onset for traits and diseases. Here, the authors develop a Bayesian approach to improve prediction in timing-related phenotypes and perform age-of-onset analyses across complex traits in the UK Biobank.
- Sven E. Ojavee
- , Athanasios Kousathanas
- & Matthew R. Robinson
-
Article
| Open AccessThe effect of eviction moratoria on the transmission of SARS-CoV-2
Massive unemployment during the COVID-19 pandemic could result in an eviction crisis in US cities. Here, the authors model the effect of evictions on SARS-CoV-2 epidemics, simulating viral transmission within and among households in a theoretical and applied urban settings.
- Anjalika Nande
- , Justin Sheen
- & Alison L. Hill
-
Article
| Open AccessHeuristic machinery for thermodynamic studies of SU(N) fermions with neural networks
The detection of the effects of spin symmetry in momentum distribution of an SU(N)-symmetric Fermi gas has remained challenging. Here, the authors use supervised machine learning to connect the spin multiplicity to thermodynamic quantities associated with different parts of the momentum distribution.
- Entong Zhao
- , Jeongwon Lee
- & Gyu-Boong Jo
-
Article
| Open AccessModel-based assessment of replicability for genome-wide association meta-analysis
In genome-wide association meta-analysis, it is often difficult to find an independent dataset of sufficient size to replicate associations. Here, the authors have developed MAMBA to calculate the probability of replicability based on consistency between datasets within the meta-analysis.
- Daniel McGuire
- , Yu Jiang
- & Dajiang J. Liu
-
Article
| Open AccessUniversal resilience patterns in labor markets
Recent technological, social, and educational changes are profoundly impacting our work, but what makes labour markets resilient to those labour shocks? Here, the authors show that labour markets resemble ecological systems whose resilience depends critically on the network of skill similarities between different jobs.
- Esteban Moro
- , Morgan R. Frank
- & Iyad Rahwan
-
Article
| Open AccessLearned adaptive multiphoton illumination microscopy for large-scale immune response imaging
Multiphoton microscopy requires precise increases in excitation power with imaging depth to generate contrast without damaging the sample. Here the authors show how an adaptive illumination function can be learned from the sample’s shape and used for in vivo imaging of whole lymph nodes.
- Henry Pinkard
- , Hratch Baghdassarian
- & Laura Waller
-
Article
| Open AccessQualitative similarities and differences in visual object representations between brains and deep networks
Deep neural networks are widely considered as good models for biological vision. Here, we describe several qualitative similarities and differences in object representations between brains and deep networks that elucidate when deep networks can be considered good models for biological vision and how they can be improved.
- Georgin Jacob
- , R. T. Pramod
- & S. P. Arun
-
Article
| Open AccessNetwork community structure of substorms using SuperMAG magnetometers
During geomagnetic substorms, the energy accumulated from solar wind is abruptly transported to ionosphere. Here, the authors show application of community detection on the time-varying networks constructed from all magnetometers collaborating with the SuperMAG initiative.
- L. Orr
- , S. C. Chapman
- & W. Guo
-
Article
| Open AccessCost function dependent barren plateaus in shallow parametrized quantum circuits
Parametrised quantum circuits are a promising hybrid classical-quantum approach, but rigorous results on their effective capabilities are rare. Here, the authors explore the feasibility of training depending on the type of cost functions, showing that local ones are less prone to the barren plateau problem.
- M. Cerezo
- , Akira Sone
- & Patrick J. Coles
-
Article
| Open AccessQuantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
Machine learning algorithms offer new possibilities for automating reaction procedures. The present paper investigates automated reaction’s prediction with Molecular Transformer, the state-of-the-art model for reaction prediction, proposing a new debiased dataset for a realistic assessment of the model’s performance.
- Dávid Péter Kovács
- , William McCorkindale
- & Alpha A. Lee
-
Article
| Open AccessThe impact of contact tracing and household bubbles on deconfinement strategies for COVID-19
The COVID-19 pandemic caused many governments to impose policies restricting social interactions. Here, the authors implement an age-specific, individual-based model with data on social contacts for the Belgian population and investigate the effect of non-pharmaceutical interventions.
- Lander Willem
- , Steven Abrams
- & Niel Hens
-
Article
| Open AccessA model for the fragmentation kinetics of crumpled thin sheets
The process of thin sheet crumpling is characterized by high complexity due to an infinite number of possible configurations. Andrejevic et al. show that ordered behavior can emerge in crumpled sheets, and uncover the correspondence between crumpling and fragmentation processes.
- Jovana Andrejevic
- , Lisa M. Lee
- & Chris H. Rycroft
-
Article
| Open AccessA single inverse-designed photonic structure that performs parallel computing
Optical analog computing has so far been mostly limited to solving a single instance of a mathematical problem at a time. Here, the authors show that the linearity of the wave equation allows to solve several problems simultaneously, and demonstrate it using an MW transmissive cavity.
- Miguel Camacho
- , Brian Edwards
- & Nader Engheta
-
Article
| Open AccessData-driven control of complex networks
Controlling the behavior of a complex network usually requires a knowledge of the network dynamics. Baggio et al. propose a data-driven framework to control a complex dynamical network, effective for non-complete or random datasets, which is of relevance for power grids and neural networks.
- Giacomo Baggio
- , Danielle S. Bassett
- & Fabio Pasqualetti
-
Article
| Open AccessUnlocking history through automated virtual unfolding of sealed documents imaged by X-ray microtomography
Here, the authors present a fully automatic computational approach for reconstructing and virtually unfolding volumetric scans of locked letters with complex internal folding, producing legible images of the letter’s contents and crease pattern while preserving letterlocking evidence.
- Jana Dambrogio
- , Amanda Ghassaei
- & Erik D. Demaine