| # | Title | Journal | Year | Citations |
|---|
| 1 | Deep learning | Nature | 2015 | 52,813 |
| 2 | Reducing the Dimensionality of Data with Neural Networks | Science | 2006 | 14,686 |
| 3 | A Fast Learning Algorithm for Deep Belief Nets | Neural Computation | 2006 | 12,682 |
| 4 | Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups | IEEE Signal Processing Magazine | 2012 | 7,242 |
| 5 | cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination | Nature Methods | 2017 | 5,371 |
| 6 | The GeneMANIA prediction server: biological network integration for gene prioritization and predicting gene function | Nucleic Acids Research | 2010 | 3,436 |
| 7 | Adaptive Mixtures of Local Experts | Neural Computation | 1991 | 3,109 |
| 8 | Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition | IEEE Transactions on Audio Speech and Language Processing | 2012 | 2,273 |
| 9 | An “Electronic Fluorescent Pictograph” Browser for Exploring and Analyzing Large-Scale Biological Data Sets | PLoS ONE | 2007 | 2,236 |
| 10 | A theory of diagnosis from first principles | Artificial Intelligence | 1987 | 2,180 |
| 11 | Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules | ACS Central Science | 2018 | 1,761 |
| 12 | Deformable models in medical image analysis: a survey | Medical Image Analysis | 1996 | 1,560 |
| 13 | Human-level concept learning through probabilistic program induction | Science | 2015 | 1,507 |
| 14 | Similarity network fusion for aggregating data types on a genomic scale | Nature Methods | 2014 | 1,392 |
| 15 | A compendium of RNA-binding motifs for decoding gene regulation | Nature | 2013 | 1,281 |
| 16 | Tropos: An Agent-Oriented Software Development Methodology | Autonomous Agents and Multi-Agent Systems | 2004 | 1,175 |
| 17 | Requirements engineering | | 2000 | 1,085 |
| 18 | N6-methyladenosine modification destabilizes developmental regulators in embryonic stem cells | Nature Cell Biology | 2014 | 1,063 |
| 19 | Hybrid speech recognition with Deep Bidirectional LSTM | | 2013 | 1,021 |
| 20 | Modeling visual attention via selective tuning | Artificial Intelligence | 1995 | 1,006 |
| 21 | Evaluating WordNet-based Measures of Lexical Semantic Relatedness | Computational Linguistics | 2006 | 997 |
| 22 | The Helmholtz Machine | Neural Computation | 1995 | 990 |
| 23 | TurboPixels: Fast Superpixels Using Geometric Flows | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2009 | 954 |
| 24 | Learning multiple layers of representation | Trends in Cognitive Sciences | 2007 | 907 |
| 25 | The Evolutionary Landscape of Alternative Splicing in Vertebrate Species | Science | 2012 | 905 |
| 26 | Semantic hashing | International Journal of Approximate Reasoning | 2009 | 898 |
| 27 | HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion | International Journal of Computer Vision | 2010 | 851 |
| 28 | Computation of component image velocity from local phase information | International Journal of Computer Vision | 1990 | 849 |
| 29 | The "wake-sleep" algorithm for unsupervised neural networks | Science | 1995 | 826 |
| 30 | (null) | International Journal of Computer Vision | 1998 | 816 |
| 31 | GeneMANIA: a real-time multiple association network integration algorithm for predicting gene function | Genome Biology | 2008 | 795 |
| 32 | Improving deep neural networks for LVCSR using rectified linear units and dropout | | 2013 | 788 |
| 33 | Lesioning an attractor network: Investigations of acquired dyslexia. | Psychological Review | 1991 | 778 |
| 34 | Robust online appearance models for visual tracking | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2003 | 766 |
| 35 | A reference map of the human binary protein interactome | Nature | 2020 | 724 |
| 36 | Gaussian Process Dynamical Models for Human Motion | IEEE Transactions on Pattern Analysis and Machine Intelligence | 2008 | 713 |
| 37 | Representing and using nonfunctional requirements: a process-oriented approach | IEEE Transactions on Software Engineering | 1992 | 684 |
| 38 | Factorial Hidden Markov Models | | 1997 | 674 |
| 39 | Deep convolutional neural networks for LVCSR | | 2013 | 671 |
| 40 | Analyzing vision at the complexity level | Behavioral and Brain Sciences | 1990 | 667 |
| 41 | Dynamic modularity in protein interaction networks predicts breast cancer outcome | Nature Biotechnology | 2009 | 654 |
| 42 | High-Throughput Mapping of a Dynamic Signaling Network in Mammalian Cells | Science | 2005 | 651 |
| 43 | Semantic Understanding of Scenes Through the ADE20K Dataset | International Journal of Computer Vision | 2019 | 649 |
| 44 | The intractability of resolution | Theoretical Computer Science | 1985 | 648 |
| 45 | Dynamic 3D models with local and global deformations: deformable superquadrics | IEEE Transactions on Pattern Analysis and Machine Intelligence | 1991 | 642 |
| 46 | The geometry of graphs and some of its algorithmic applications | Combinatorica | 1995 | 642 |
| 47 | Sensitive tumour detection and classification using plasma cell-free DNA methylomes | Nature | 2018 | 624 |
| 48 | Protein complex prediction via cost-based clustering | Bioinformatics | 2004 | 620 |
| 49 | The relative efficiency of propositional proof systems | Journal of Symbolic Logic | 1979 | 612 |
| 50 | Complement reducible graphs | Discrete Applied Mathematics | 1981 | 612 |
