Nature Machine Intelligence

Papers
(The TQCC of Nature Machine Intelligence is 29. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2020-04-01 to 2024-04-01.)
ArticleCitations
An interpretable mortality prediction model for COVID-19 patients661
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators596
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans592
Shortcut learning in deep neural networks553
Secure, privacy-preserving and federated machine learning in medical imaging482
Drug discovery with explainable artificial intelligence422
Deep learning for tomographic image reconstruction240
Machine learning pipeline for battery state-of-health estimation238
AI for radiographic COVID-19 detection selects shortcuts over signal233
An open source machine learning framework for efficient and transparent systematic reviews225
Molecular contrastive learning of representations via graph neural networks188
Inverse design of nanoporous crystalline reticular materials with deep generative models171
Finding key players in complex networks through deep reinforcement learning170
Expanding functional protein sequence spaces using generative adversarial networks166
Ensemble deep learning in bioinformatics159
End-to-end privacy preserving deep learning on multi-institutional medical imaging158
Geometry-enhanced molecular representation learning for property prediction155
The carbon impact of artificial intelligence154
Causal inference and counterfactual prediction in machine learning for actionable healthcare150
Improved protein structure prediction by deep learning irrespective of co-evolution information140
Concept whitening for interpretable image recognition121
Mapping the space of chemical reactions using attention-based neural networks121
Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks121
Development of metaverse for intelligent healthcare118
Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation114
The rise of robots in surgical environments during COVID-19107
Database-independent molecular formula annotation using Gibbs sampling through ZODIAC102
Deep learning-based prediction of the T cell receptor–antigen binding specificity101
Geometric deep learning on molecular representations101
A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing100
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science100
Bioinspired acousto-magnetic microswarm robots with upstream motility99
Neural circuit policies enabling auditable autonomy97
Advances, challenges and opportunities in creating data for trustworthy AI96
Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion95
Code-free deep learning for multi-modality medical image classification94
Dual use of artificial-intelligence-powered drug discovery93
Estimation of continuous valence and arousal levels from faces in naturalistic conditions93
A soft robot that adapts to environments through shape change92
Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network91
Making deep neural networks right for the right scientific reasons by interacting with their explanations91
Machine learning and computation-enabled intelligent sensor design91
Towards a new generation of artificial intelligence in China91
High-accuracy prostate cancer pathology using deep learning89
Prediction of water stability of metal–organic frameworks using machine learning89
Exploring the limit of using a deep neural network on pileup data for germline variant calling89
Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms89
Origami-inspired miniature manipulator for teleoperated microsurgery89
scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data88
Deep learning incorporating biologically inspired neural dynamics and in-memory computing87
Automating turbulence modelling by multi-agent reinforcement learning86
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning83
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors83
Machine learning and algorithmic fairness in public and population health82
Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis81
Artificial intelligence cooperation to support the global response to COVID-1980
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks77
Controllable protein design with language models77
The transformational role of GPU computing and deep learning in drug discovery77
Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning75
Using online verification to prevent autonomous vehicles from causing accidents74
Three types of incremental learning73
Improving performance of deep learning models with axiomatic attribution priors and expected gradients72
A soft thumb-sized vision-based sensor with accurate all-round force perception71
Morphological and molecular breast cancer profiling through explainable machine learning71
Stable learning establishes some common ground between causal inference and machine learning71
A definition, benchmark and database of AI for social good initiatives71
An embedded ethics approach for AI development70
Learning functional properties of proteins with language models70
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images70
Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations68
A geometric deep learning approach to predict binding conformations of bioactive molecules68
Predictive control of aerial swarms in cluttered environments67
Biological underpinnings for lifelong learning machines66
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning62
AI-generated characters for supporting personalized learning and well-being61
Governing AI safety through independent audits61
Teaching recurrent neural networks to infer global temporal structure from local examples60
Large pre-trained language models contain human-like biases of what is right and wrong to do60
A neural network trained for prediction mimics diverse features of biological neurons and perception59
Extraction of protein dynamics information from cryo-EM maps using deep learning57
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin57
A case-based interpretable deep learning model for classification of mass lesions in digital mammography57
Simultaneous deep generative modelling and clustering of single-cell genomic data56
A transformer-based model to predict peptide–HLA class I binding and optimize mutated peptides for vaccine design56
Combinatorial optimization with physics-inspired graph neural networks55
Learning function from structure in neuromorphic networks54
Predicting tumour mutational burden from histopathological images using multiscale deep learning53
Deep neural networks identify sequence context features predictive of transcription factor binding53
A shallow convolutional neural network predicts prognosis of lung cancer patients in multi-institutional computed tomography image datasets53
Large-scale chemical language representations capture molecular structure and properties53
Encoding of tactile information in hand via skin-integrated wireless haptic interface53
Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions52
When causal inference meets deep learning52
Human–AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support51
Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes51
Molecular convolutional neural networks with DNA regulatory circuits50
Interpretable deep-learning models to help achieve the Sustainable Development Goals50
Fast and energy-efficient neuromorphic deep learning with first-spike times49
Parameter-efficient fine-tuning of large-scale pre-trained language models49
Chemically programmable microrobots weaving a web from hormones48
Benchmarking saliency methods for chest X-ray interpretation48
Self-supervised retinal thickness prediction enables deep learning from unlabelled data to boost classification of diabetic retinopathy47
Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media47
Improving representations of genomic sequence motifs in convolutional networks with exponential activations46
Machine Learning for COVID-19 needs global collaboration and data-sharing46
Chemical language models enable navigation in sparsely populated chemical space46
Large language models associate Muslims with violence45
Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework45
Improving the quality of machine learning in health applications and clinical research45
Deep variational network for rapid 4D flow MRI reconstruction44
Radiological tumour classification across imaging modality and histology44
Cell type annotation of single-cell chromatin accessibility data via supervised Bayesian embedding43
The challenges of deploying artificial intelligence models in a rapidly evolving pandemic43
External validation demonstrates limited clinical utility of the interpretable mortality prediction model for patients with COVID-1943
A machine learning platform to estimate anti-SARS-CoV-2 activities43
Multiscale simulations of complex systems by learning their effective dynamics42
Deep recurrent optical flow learning for particle image velocimetry data42
A biological perspective on evolutionary computation42
Skills for physical artificial intelligence40
Experimental discovery of structure–property relationships in ferroelectric materials via active learning39
Real-world embodied AI through a morphologically adaptive quadruped robot39
An interpretable deep-learning architecture of capsule networks for identifying cell-type gene expression programs from single-cell RNA-sequencing data39
Increasing generality in machine learning through procedural content generation39
Automatic strain sensor design via active learning and data augmentation for soft machines38
Institutionalizing ethics in AI through broader impact requirements38
A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data38
Responsible artificial intelligence in agriculture requires systemic understanding of risks and externalities38
Protein function prediction is improved by creating synthetic feature samples with generative adversarial networks37
Deep learning-inferred multiplex immunofluorescence for immunohistochemical image quantification37
Combining automated microfluidic experimentation with machine learning for efficient polymerization design37
Enhancing optical-flow-based control by learning visual appearance cues for flying robots36
A novel machine learning framework for automated biomedical relation extraction from large-scale literature repositories36
A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware36
Improving healthcare operations management with machine learning36
The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires36
Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices35
Deep learning-based robust positioning for all-weather autonomous driving34
Tracking the debate on COVID-19 surveillance tools34
The neural resource allocation problem when enhancing human bodies with extra robotic limbs34
Neurons learn by predicting future activity32
Intelligent problem-solving as integrated hierarchical reinforcement learning32
A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks32
Accelerated rational PROTAC design via deep learning and molecular simulations31
Interpretable bilinear attention network with domain adaptation improves drug–target prediction31
Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modelling31
Accelerating evidence-informed decision-making for the Sustainable Development Goals using machine learning31
Minimal-uncertainty prediction of general drug-likeness based on Bayesian neural networks31
Empirical observation of negligible fairness–accuracy trade-offs in machine learning for public policy31
Predicting myocardial infarction through retinal scans and minimal personal information31
Bringing artificial intelligence to business management31
Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports31
A deep generative model enables automated structure elucidation of novel psychoactive substances31
Quantifying the spatial homogeneity of urban road networks via graph neural networks30
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments30
Automating crystal-structure phase mapping by combining deep learning with constraint reasoning30
Deep learning STEM-EDX tomography of nanocrystals30
Autoregressive neural-network wavefunctions for ab initio quantum chemistry30
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence30
Understanding adversarial examples requires a theory of artefacts for deep learning29
Artificial intelligence in a crisis needs ethics with urgency29
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition29
0.041391134262085