Nature Machine Intelligence

(The TQCC of Nature Machine Intelligence is 26. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 500 papers]. The publications cover those that have been published in the past four years, i.e., from 2019-09-01 to 2023-09-01.)
From local explanations to global understanding with explainable AI for trees2125
The global landscape of AI ethics guidelines1215
An interpretable mortality prediction model for COVID-19 patients617
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans498
Shortcut learning in deep neural networks384
Secure, privacy-preserving and federated machine learning in medical imaging371
Principles alone cannot guarantee ethical AI366
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators359
Drug discovery with explainable artificial intelligence302
Predicting the state of charge and health of batteries using data-driven machine learning259
Deep learning for tomographic image reconstruction168
Machine learning pipeline for battery state-of-health estimation166
AI for radiographic COVID-19 detection selects shortcuts over signal161
In situ training of feed-forward and recurrent convolutional memristor networks156
An open source machine learning framework for efficient and transparent systematic reviews137
Machine learning for active matter135
Inverse design of nanoporous crystalline reticular materials with deep generative models129
Deep learning optoacoustic tomography with sparse data126
Finding key players in complex networks through deep reinforcement learning123
Causal inference and counterfactual prediction in machine learning for actionable healthcare119
Improved protein structure prediction by deep learning irrespective of co-evolution information119
Predicting drug–protein interaction using quasi-visual question answering system115
Ensemble deep learning in bioinformatics115
End-to-end privacy preserving deep learning on multi-institutional medical imaging112
Expanding functional protein sequence spaces using generative adversarial networks111
Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks100
The rise of robots in surgical environments during COVID-1996
Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks96
The carbon impact of artificial intelligence94
Rapid online learning and robust recall in a neuromorphic olfactory circuit94
Fully portable and wireless universal brain–machine interfaces enabled by flexible scalp electronics and deep learning algorithm92
Shared human–robot proportional control of a dexterous myoelectric prosthesis88
Molecular contrastive learning of representations via graph neural networks88
Clinically applicable deep learning framework for organs at risk delineation in CT images86
Generative molecular design in low data regimes85
Concept whitening for interpretable image recognition84
Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation84
Mapping the space of chemical reactions using attention-based neural networks83
Geometry-enhanced molecular representation learning for property prediction82
Prediction of drug combination effects with a minimal set of experiments81
Database-independent molecular formula annotation using Gibbs sampling through ZODIAC78
A topology-based network tree for the prediction of protein–protein binding affinity changes following mutation78
Exploring the limit of using a deep neural network on pileup data for germline variant calling75
A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing74
Artificial intelligence cooperation to support the global response to COVID-1973
A soft robot that adapts to environments through shape change71
High-accuracy prostate cancer pathology using deep learning70
Machine learning and computation-enabled intelligent sensor design70
Neural circuit policies enabling auditable autonomy68
Human action recognition with a large-scale brain-inspired photonic computer68
Making deep neural networks right for the right scientific reasons by interacting with their explanations67
Deep learning incorporating biologically inspired neural dynamics and in-memory computing67
Prediction of water stability of metal–organic frameworks using machine learning66
Code-free deep learning for multi-modality medical image classification66
Deep learning robotic guidance for autonomous vascular access66
Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network66
Origami-inspired miniature manipulator for teleoperated microsurgery65
Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis65
Behavioural evidence for a transparency–efficiency tradeoff in human–machine cooperation65
Towards a new generation of artificial intelligence in China65
Automating turbulence modelling by multi-agent reinforcement learning64
Bioinspired acousto-magnetic microswarm robots with upstream motility63
Deep-learning-based prediction of late age-related macular degeneration progression63
Deep learning-based prediction of the T cell receptor–antigen binding specificity62
Trusting artificial intelligence in cybersecurity is a double-edged sword62
Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms62
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors61
Homeostasis and soft robotics in the design of feeling machines60
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science60
Towards ethical and socio-legal governance in AI59
Geometric deep learning on molecular representations58
Estimation of continuous valence and arousal levels from faces in naturalistic conditions58
Machine learning and algorithmic fairness in public and population health55
An embedded ethics approach for AI development55
Morphological and molecular breast cancer profiling through explainable machine learning55
Benchmarks for progress in neuromorphic computing55
Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion54
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images54
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning53
Dual use of artificial-intelligence-powered drug discovery51
Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations51
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks50
Using online verification to prevent autonomous vehicles from causing accidents49
Extraction of protein dynamics information from cryo-EM maps using deep learning48
A neural network trained for prediction mimics diverse features of biological neurons and perception46
A definition, benchmark and database of AI for social good initiatives45
Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning45
Simultaneous deep generative modelling and clustering of single-cell genomic data44
A portable three-degrees-of-freedom force feedback origami robot for human–robot interactions44
Governing AI safety through independent audits43
Teaching recurrent neural networks to infer global temporal structure from local examples42
Development of metaverse for intelligent healthcare42
Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions42
Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes42
Deep neural networks identify sequence context features predictive of transcription factor binding42
A soft thumb-sized vision-based sensor with accurate all-round force perception41
Machine Learning for COVID-19 needs global collaboration and data-sharing41
Learning functional properties of proteins with language models41
Stable learning establishes some common ground between causal inference and machine learning41
Improving performance of deep learning models with axiomatic attribution priors and expected gradients41
Automated abnormality detection in lower extremity radiographs using deep learning40
A shallow convolutional neural network predicts prognosis of lung cancer patients in multi-institutional computed tomography image datasets40
Improving the quality of machine learning in health applications and clinical research40
Predicting disease-associated mutation of metal-binding sites in proteins using a deep learning approach40
A transformer-based model to predict peptide–HLA class I binding and optimize mutated peptides for vaccine design40
Predicting tumour mutational burden from histopathological images using multiscale deep learning40
A geometric deep learning approach to predict binding conformations of bioactive molecules39
Predictive control of aerial swarms in cluttered environments39
Validity of machine learning in biology and medicine increased through collaborations across fields of expertise39
Deep variational network for rapid 4D flow MRI reconstruction38
Chemically programmable microrobots weaving a web from hormones38
The challenges of deploying artificial intelligence models in a rapidly evolving pandemic38
When causal inference meets deep learning38
Advances, challenges and opportunities in creating data for trustworthy AI38
External validation demonstrates limited clinical utility of the interpretable mortality prediction model for patients with COVID-1938
Deep learning of circulating tumour cells37
Controllable protein design with language models37
Fast and energy-efficient neuromorphic deep learning with first-spike times36
Self-supervised retinal thickness prediction enables deep learning from unlabelled data to boost classification of diabetic retinopathy36
Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media35
A machine learning platform to estimate anti-SARS-CoV-2 activities35
Improving representations of genomic sequence motifs in convolutional networks with exponential activations35
A case-based interpretable deep learning model for classification of mass lesions in digital mammography34
Tracking the debate on COVID-19 surveillance tools34
Combining automated microfluidic experimentation with machine learning for efficient polymerization design34
The transformational role of GPU computing and deep learning in drug discovery34
Learning function from structure in neuromorphic networks33
Deep convolutional neural networks in the face of caricature33
Radiological tumour classification across imaging modality and histology32
Chemical language models enable navigation in sparsely populated chemical space32
An interpretable deep-learning architecture of capsule networks for identifying cell-type gene expression programs from single-cell RNA-sequencing data32
Skills for physical artificial intelligence31
A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data31
Interpretable deep-learning models to help achieve the Sustainable Development Goals31
Real-world embodied AI through a morphologically adaptive quadruped robot30
Enhancing optical-flow-based control by learning visual appearance cues for flying robots30
A biological perspective on evolutionary computation30
Increasing generality in machine learning through procedural content generation30
Biological underpinnings for lifelong learning machines30
Accurate data-driven prediction does not mean high reproducibility29
Deep recurrent optical flow learning for particle image velocimetry data29
Combinatorial optimization with physics-inspired graph neural networks29
Molecular convolutional neural networks with DNA regulatory circuits29
A fast neural network approach for direct covariant forces prediction in complex multi-element extended systems29
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning28
A novel machine learning framework for automated biomedical relation extraction from large-scale literature repositories28
Large language models associate Muslims with violence28
Multiscale simulations of complex systems by learning their effective dynamics28
Protein function prediction is improved by creating synthetic feature samples with generative adversarial networks28
AmoebaContact and GDFold as a pipeline for rapid de novo protein structure prediction28
scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data27
AI-generated characters for supporting personalized learning and well-being26
Institutionalizing ethics in AI through broader impact requirements26
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin26
Cell type annotation of single-cell chromatin accessibility data via supervised Bayesian embedding26