Deep learning View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2015-05-27

AUTHORS

Yann LeCun, Yoshua Bengio, Geoffrey Hinton

ABSTRACT

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech. More... »

PAGES

436-444

Journal

TITLE

Nature

ISSUE

7553

VOLUME

521

Related Patents

  • Superconducting Nanowire-Based Programmable Processor
  • Computer-Based Method For Analyzing An Electrode Layer Of A Battery Cell By Means Of An Ai Engine, Method For Training An Ai Engine, Manufacturing Method Of A Battery Storage Device And Manufacturing Unit
  • Device For Determining A Caption For An Unknown Traffic Sign
  • Dueling Deep Neural Networks
  • Methods For Real-Time Skill Assessment Of Multi-Step Tasks Performed By Hand Movements Using A Video Camera
  • Method And Device For Showing The Influence Of Cutting Parameters On A Cut Edge
  • Deep Machine Learning Methods And Apparatus For Robotic Grasping
  • Apparatus And Method For Monitoring And Controlling Of A Neural Network Using Another Neural Network Implemented On One Or More Solid-State Chips
  • Method And Apparatus For Applying Deep Learning Techniques In Video Coding, Restoration And Video Quality Analysis (Vqa)
  • Noise And Signal Management For Rpu Array
  • Flow Analysis In 4d Mr Image Data
  • Linear Photonic Processors And Related Methods
  • Controller Systems And Methods Of Limiting The Operation Of Neural Networks To Be Within One Or More Conditions
  • Path-Number-Balanced Universal Photonic Network
  • Current Crowding In Three-Terminal Superconducting Devices And Related Methods
  • Bio-Marker Composition For Sensitivity Prediction Of Igfr Drug, Estimation Method For Sensitivity Prediction Of Igfr Drug Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Sensitivity Prediction Of Igfr Drug
  • System And Method For Compact And Efficient Sparse Neural Networks
  • System And Method For Multi-Architecture Computed Tomography Pipeline
  • High-Speed Delay Scanning And Deep Learning Techniques For Spectroscopic Srs Imaging
  • Determining Biomarkers From Histopathology Slide Images
  • High-Speed And High-Precision Photonic Analog-To-Digital Conversion Device And Method For Realizing Intelligent Signal Processing Using The Same
  • Analysis Of Perturbed Subjects Using Semantic Embeddings
  • System And Method For Training Deep Learning Classification Networks
  • Automated Adjustment Of The Undersampling Factor
  • Image Processing Methods And Apparatus, And Electronic Devices
  • Method And Spectrometer Apparatus For Investigating An Infrared Absorption Of A Sample
  • Dueling Deep Neural Networks
  • Apparatus And Methods For Optical Neural Network
  • Noise-Robust Neural Networks And Methods Thereof
  • Scaled Compute Fabric For Accelerated Deep Learning
  • Methods And Systems For Detecting Malicious Webpages
  • Tensor-Based Deep Relevance Model For Search On Online Social Networks
  • Dynamic, Automated Fulfillment Of Computer-Based Resource Request Provisioning Using Deep Reinforcement Learning
  • System And Method For A Deep Learning Machine For Object Detection
  • Programmable Photonic Processing
  • Method For Analyzing An Electrode Layer Of A Battery Storage Device, Method For Producing A Battery Storage Device, And Production Unit
  • Multiply-Accumulate “0” Data Gating
  • Hybrid Analog-Digital Matrix Processors
  • Automated Pattern Recognition And Scoring Method Of Histological Images
  • Neural Network For Processing Graph Data
  • Bio-Marker Composition For Prediction Of Drug For Head And Neck Cancer Sensitivity, Estimation Method For Prediction Of Drug For Head And Neck Cancer Sensitivity Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Prediction Of Drug For Head And Neck Cancer Sensitivity
  • Apparatus And Methods For Optical Neural Network
  • Object Detection In Point Clouds
  • Method And Apparatus For Neural Network Quantization
  • Method And System For Artificial Intelligence Based Medical Image Segmentation
  • Neural Network For Processing Graph Data
  • System And Method For Automated Seismic Interpretation
  • Method Of Identifying A Drug For Patient-Specific Treatment
  • System And Method For Creating And Managing An Interactive Network Of Applications
  • Apparatus And Methods For Optical Neural Network
  • Wavelet Representation For Accelerated Deep Learning
  • Isa Enhancements For Accelerated Deep Learning
  • Method For Building A Neural Network For Simulating Physical Systems
  • Tiling Image Compression Using Neural Network
  • Bio-Marker Composition For Sensitivity Prediction Of Mitosis Drug, Estimation Method For Sensitivity Prediction Of Mitosis Drug Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Sensitivity Prediction Of Mitosis Drug
  • Neuron Smearing For Accelerated Deep Learning
  • Display Assistance Solution For Simulating An Auto-Exposure Process
  • Superresolution Metrology Methods Based On Singular Distributions And Deep Learning
  • Use Of Comprehensive Artificial Intelligence In Primary Industry Facilities
  • Photonic Processing Systems And Methods
  • Reconstructing Time Series Datasets With Missing Values Utilizing Machine Learning
  • Bio-Marker For Prediction Of Drug Sensitivity, Estimation Method For Prediction Of Drug Sensitivity And Diagnosing Chip For Prediction Of Drug Sensitivity
  • Deep Machine Learning Methods And Apparatus For Robotic Grasping
  • Signal Retrieval Apparatus, Method, And Program
  • Apparatus, Systems, And Methods For Nonblocking Optical Switching
  • Control Policies For Collective Robot Learning
  • Dataflow Triggered Tasks For Accelerated Deep Learning
  • System And Method For Seismic Facies Identification Using Machine Learning
  • Predicting Total Nucleic Acid Yield And Dissection Boundaries For Histology Slides
  • System And Method For Automated Funduscopic Image Analysis
  • Controller Systems And Methods Of Limiting The Operation Of Neural Networks To Be Within One Or More Conditions
  • Bio-Marker Composition For Sensitivity Prediction Of Chromatin Drug, Estimation Method For Sensitivity Prediction Of Chromatin Drug Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Sensitivity Prediction Of Chromatin Drug
  • System For Monitoring Compliance With Oral Hygiene And Tele-Dentistry System
  • Bio-Marker Composition For Prediction Of Drug For Bone Cancer Sensitivity, Estimation Method For Prediction Of Drug For Bone Cancer Sensitivity Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Prediction Of Drug For Bone Cancer Sensitivity
  • Deep Learning Approach To Identify Comparative Reference Incidents
  • Programmable Photonic Processing
  • Bio-Marker Composition For Sensitivity Prediction Of Erk_Mapk Drug, Estimation Method For Sensitivity Prediction Of Erk_Mapk Drug Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Sensitivity Prediction Of Erk_Mapk Drug
  • Training Action Selection Neural Networks Using Look-Ahead Search
  • Neural Network For Processing Graph Data
  • Extracting Gradient Features From Neural Networks
  • Method For Evaluating A State Of A Three-Dimensional Test Object And Corresponding Evaluation System
  • Energy Demand Prediction System
  • Methods And Systems For Guidance In Cardiac Resynchronization Therapy
  • Systems And Methods For Callable Options Values Determination Using Deep Machine Learning
  • Generative Attribute Optimization
  • Compressive Sensing Capturing Device And Method
  • Real-Number Photonic Encoding
  • Extracting Gradient Features From Neural Networks
  • Methods And Systems For Human Tissue Analysis Using Shearlet Transforms
  • Predicting Total Nucleic Acid Yield And Dissection Boundaries For Histology Slides
  • Adaptive And Interchangeable Neural Networks
  • Task Synchronization For Accelerated Deep Learning
  • Deep Learning Based Method And Device For Noise Suppression And Distortion Correction Of Analog-To-Digital Converters
  • Data Structure Descriptors For Deep Learning Acceleration
  • Method Of Predicting Response To Chimeric Antigen Receptor Therapy
  • Magnetic Resonance System And Method For Producing Images
  • Systems And Methods For Labeling Large Datasets Of Physiological Records Based On Unsupervised Machine Learning
  • Visualization Aid Solution To Simulate A Self-Exposure Process
  • Memory Device Including A Processing Circuit, Memory Controller Controlling The Memory Device And Memory System Including The Memory Device
  • Systems And Methods For Training Matrix-Based Differentiable Programs
  • Method, Computer Program Product, And Device Comprising Such A Product For Displaying The Influence Of Cutting Parameters On A Cutting Edge
  • Linear Photonic Processors And Related Methods
  • Optical Ising Machines And Optical Convolutional Neural Networks
  • Classifying Images Of Dose-Response Graphs
  • Seismic Embeddings For Detecting Subsurface Hydrocarbon Presence And Geological Features
  • Computer-Based Method For Analyzing A Battery Cell, Manufacturing Method For Battery Storage, Manufacturing Unit And Computer Program Product
  • Optical Processing System
  • Hybrid Analog-Digital Matrix Processors
  • Long-Term And Continuous Animal Behavioral Monitoring
  • Methods, Systems, Apparatus And Articles Of Manufacture For Receipt Decoding
  • Predicting Total Nucleic Acid Yield And Dissection Boundaries For Histology Slides
  • Bio-Marker Composition For Prediction Of Drug Sensitivity, Estimation Method For Prediction Of Drug Sensitivity Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Prediction Of Drug Sensitivity
  • Systems And Methods For Clinical Decision Making For A Patient Receiving A Neuromodulation Therapy Based On Deep Learning
  • Parsimonious Inference On Convolutional Neural Networks
  • Bio-Marker Composition For Prediction Of Drug For Blood Cancer Sensitivity, Estimation Method For Prediction Of Drug For Blood Cancer Sensitivity Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Prediction Of Drug For Blood Cancer Sensitivity
  • Methods And Systems For Data Traffic Analysis
  • Apparatus And Method For Monitoring And Controlling Of A Neural Network Using Another Neural Network Implemented On One Or More Solid-State Chips
  • Cross-Domain Shortlisting
  • High-Efficiency Multi-Slot Waveguide Nano-Opto-Electromechanical Phase Modulator
  • Method For Analysing Medical Treatment Data Based On Deep Learning And Intelligence Analyser Thereof
  • Intelligent Design Structure Selection In An Internet Of Things (Iot) Computing Environment
  • Method And System For Artificial Intelligence Based Medical Image Segmentation
  • Visual Analytics System For Convolutional Neural Network Based Classifiers
  • Systems And Methods For Processing Of Dental Images
  • Phenotype Analysis Of Cellular Image Data Using A Deep Metric Network
  • Unsupervised Deep Representation Learning For Fine-Grained Body Part Recognition
  • System, In Particular Magnetic Resonance System, For Producing Images
  • Discovery Of An Inexplicit Link Between A Change And An Incident In A Computing Environment
  • Data Structure Descriptors For Deep Learning Acceleration
  • Seizure Onset Classification And Stimulation Parameter Selection
  • Processor Element Redundancy For Accelerated Deep Learning
  • Procedure For A Measuring System In The Vehicle For The Detection And Classification Of Objects In The Area Around The Vehicle Using A Deep Learning Procedure With A Self-Learning Decision Maker
  • Methods And Systems For Malware Detection And Categorization
  • Systems And Methods For Synthetic Medical Image Generation
  • Artificial Intelligence Segmentation Of Tissue Images
  • Bio-Marker Composition For Prediction Of Drug For Brain Cancer Sensitivity, Estimation Method For Prediction Of Drug For Brain Cancer Sensitivity Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Prediction Of Drug For Brain Cancer Sensitivity
  • Prostate Cancer Tissue Image Classification With Deep Learning
  • Hybrid Analog-Digital Matrix Processors
  • Phenotype Analysis Of Cellular Image Data Using A Deep Metric Network
  • Controller Systems And Methods Of Limiting The Operation Of Neural Networks To Be Within One Or More Conditions
  • Systems, Methods And Media For Automatically Generating A Bone Age Assessment From A Radiograph
  • Drug Sensitivity Related Gene Expression And Copy Number Variation Based Functional Haplotyping Methods And System
  • Optoelectronic Computing Systems
  • System And Method For Ranking Of Hybrid Speech Recognition Results With Neural Networks
  • Detection Of Hydrocarbon Presence In Subsurface From Seismic Images Using Relational Learning
  • Self-Correcting Controller Systems And Methods Of Limiting The Operation Of Neural Networks To Be Within One Or More Conditions
  • Method And Apparatus For Applying Deep Learning Techniques In Video Coding, Restoration And Video Quality Analysis (Vqa)
  • Joint Deep Learning For Land Cover And Land Use Classification
  • Adaptive And Interchangeable Neural Networks
  • Automated Seismic Interpretation Using Fully Convolutional Neural Networks
  • Method, Device And System For Dynamic Analysis From Sequences Of Volumetric Images
  • System And Method For Spectral Computed Tomography Using Single Polychromatic X-Ray Spectrum Acquisition
  • Bio-Marker Composition For Prediction Of Drug For Lung Cancer Sensitivity, Estimation Method For Prediction Of Drug For Lung Cancer Sensitivity Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Prediction Of Drug For Lung Cancer Sensitivity
  • Controller Systems And Methods Of Limiting The Operation Of Neural Networks To Be Within One Or More Conditions
  • Methods And Systems For Pattern Characteristic Detection
  • Process For An Ultrasonic Measuring System In The Vehicle For The Detection And Classification Of Objects In The Area Around The Vehicle With The Help Of A Deep Learning Process And A Self-Learning Decision Maker
  • Group Of Neural Networks Ensuring Integrity
  • System And Method For Creating And Managing An Interactive Network Of Applications
  • Multiply-Accumulate “0” Data Gating
  • Gene Editing System For Correcting Splicing Defects
  • Attendee Engagement Determining System And Method
  • Methods And Systems For Malware Detection
  • Tile Image Compression Using Neural Networks
  • Self-Correcting Controller Systems And Methods Of Limiting The Operation Of Neural Networks To Be Within One Or More Conditions
  • Serialized Electro-Optic Neural Network Using Optical Weights Encoding
  • Automated Adjustment Of The Undersampling Factor
  • Determining Biomarkers From Histopathology Slide Images
  • Optical Differential Low-Noise Receivers And Related Methods
  • Use Of Comprehensive Artificial Intelligence In Primary Industry Plants
  • Image Segmentation Using Neural Networks
  • Systems And Methods For Clinical Decision Making For A Patient Receiving A Neuromodulation Therapy Based On Deep Learning
  • Generating Automated Assistant Responses And/Or Actions Directly From Dialog History And Resources
  • Bio-Marker Composition For Prediction Of Drug For Breast/Ovary Cancer Sensitivity, Estimation Method For Prediction Of Drug For Breast/Ovary Cancer Sensitivity Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Prediction Of Drug For Breast/Ovary Cancer Sensitivity
  • Systems And Methods For Analog Computing Using A Linear Photonic Processor
  • Apparatus And Method For Augmented Reality
  • Synchronous Convergent Pulses Reduce Dimensions Of Serial Surfaces
  • Method And Apparatus For Processing Nuclear Magnetic Resonance And Magnetic Resonance Spectroscopy Data Based On Artificial Neural Network
  • A Computer-Implemented Method For Training An Artificial Neural Network, Method For Inspecting A Component, Test System For Examining Components, And Computer Program
  • Systems And Methods For Training Matrix-Based Differentiable Programs
  • Training Of Artificial Neural Networks Using Safe Mutations Based On Output Gradients
  • Control Wavelet For Accelerated Deep Learning
  • Method, Device And System For Dynamic Analysis From Sequences Of Volumetric Images
  • Encoding And Decoding Image Data
  • Methods And Systems For In-Bed Pose Estimation
  • Bio-Marker Composition For Sensitivity Prediction Of Egfr Drug, Estimation Method For Sensitivity Prediction Of Egfr Drug Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Sensitivity Prediction Of Egfr Drug
  • Systems And Methods For Activation Functions For Photonic Neural Networks
  • Image And Text Data Hierarchical Classifiers
  • Deep Machine Learning Methods And Apparatus For Robotic Grasping
  • Photonic Processing Systems And Methods
  • Performing Navigation Tasks Using Grid Codes
  • Synchronized Pulses Identify And Locate Targets Rapidly
  • Processing Fundus Images Using Machine Learning Models To Generate Blood-Related Predictions
  • Deep Machine Learning Methods And Apparatus For Robotic Grasping
  • High-Efficiency Multi-Slot Waveguide Nano-Opto-Electromechanical Phase Modulator
  • Deep Machine Learning Methods And Apparatus For Robotic Grasping
  • Method For Rating A State Of A Three-Dimensional Test Object, And Corresponding Rating System
  • Computer-Supported Method For Analyzing A Battery Cell, Method For Producing A Battery Storage Device, Production Unit, And Computer Program Product
  • Predicting Labels Using A Deep-Learning Model
  • Multiple-Action Computational Model Training And Operation
  • Oral Hygiene System For Compliance Monitoring And Tele-Dentistry System
  • Methods And Systems For Malware Detection
  • Bio-Marker Composition For Prediction Of Drug Sensitivity, Estimation Method For Prediction Of Drug Sensitivity Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Prediction Of Drug Sensitivity
  • Apparatus, System And Method For Machine Learning Spike Noise Detection
  • Augmented Reality Microscope For Pathology
  • Method And System For Artificial Intelligence Based Medical Image Segmentation
  • Apparatus, Systems, And Methods For Nonblocking Optical Switching
  • Accelerated Deep Learning
  • Backpressure For Accelerated Deep Learning
  • Fabric Vectors For Deep Learning Acceleration
  • Apparatus And Method For Monitoring And Controlling Of A Neural Network Using Another Neural Network Implemented On One Or More Solid-State Chips
  • Microthreading For Accelerated Deep Learning
  • Making Object-Level Predictions Of The Future State Of A Physical System
  • Apparatus And Method For Monitoring And Controlling Of A Neural Network Using Another Neural Network Implemented On One Or More Solid-State Chips
  • Medical Data Processing Device, Magnetic Resonance Imaging Device, And Learned Model Generation Method
  • Systems And Methods For Decoding Code-Multiplexed Coulter Signals Using Machine Learning
  • Performing Navigation Tasks Using Grid Codes
  • Task Activating For Accelerated Deep Learning
  • Predicting Labels Using A Deep-Learning Model
  • Method Of Neural Network Construction For The Simulation Of Physical Systems
  • Bio-Marker Composition For Prediction Of Drug For Blood Cancer Sensitivity, Estimation Method For Prediction Of Drug For Blood Cancer Sensitivity Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Prediction Of Drug For Blood Cancer Sensitivity
  • Photonics Packaging Method And Device
  • Computer-Supported Method For Analyzing An Electrode Layer Of A Battery Cell Using A Ki Engine, Method For Training A Ki Engine, Method For Producing A Battery Storage Device, And Production Unit
  • Bio-Marker Composition For Sensitivity Prediction Of Abl Drug, Estimation Method For Sensitivity Prediction Of Abl Drug Using Bio-Marker Composition And Diagnosing Chip For Detection Of Bio-Marker Composition For Sensitivity Prediction Of Abl Drug
  • System And Method For Automated Seismic Interpretation
  • Neural-Network State-Of-Charge Estimation
  • Adaptive And Interchangeable Neural Networks Utilizing Predicting Information
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1038/nature14539

    DOI

    http://dx.doi.org/10.1038/nature14539

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1010020120

    PUBMED

    https://www.ncbi.nlm.nih.gov/pubmed/26017442


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/17", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Psychology and Cognitive Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Psychology", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1702", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Cognitive Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Algorithms", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Artificial Intelligence", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Computers", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Language", 
            "type": "DefinedTerm"
          }, 
          {
            "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
            "name": "Neural Networks, Computer", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "New York University, 715 Broadway, 10003, New York, New York, USA", 
              "id": "http://www.grid.ac/institutes/grid.137628.9", 
              "name": [
                "Facebook AI Research, 770 Broadway, 10003, New York, New York, USA", 
                "New York University, 715 Broadway, 10003, New York, New York, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "LeCun", 
            "givenName": "Yann", 
            "id": "sg:person.0765036655.42", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0765036655.42"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Computer Science and Operations Research Universit\u00e9 de Montr\u00e9al, Pavillon Andr\u00e9-Aisenstadt, PO Box 6128 Centre-Ville STN, H3C 3J7, Montr\u00e9al, Quebec, Canada", 
              "id": "http://www.grid.ac/institutes/grid.14848.31", 
              "name": [
                "Department of Computer Science and Operations Research Universit\u00e9 de Montr\u00e9al, Pavillon Andr\u00e9-Aisenstadt, PO Box 6128 Centre-Ville STN, H3C 3J7, Montr\u00e9al, Quebec, Canada"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Bengio", 
            "givenName": "Yoshua", 
            "id": "sg:person.01303456133.13", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01303456133.13"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Computer Science, University of Toronto, 6 King's College Road, M5S 3G4, Toronto, Ontario, Canada", 
              "id": "http://www.grid.ac/institutes/grid.17063.33", 
              "name": [
                "Google, 1600 Amphitheatre Parkway, 94043, Mountain View, California, USA", 
                "Department of Computer Science, University of Toronto, 6 King's College Road, M5S 3G4, Toronto, Ontario, Canada"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Hinton", 
            "givenName": "Geoffrey", 
            "id": "sg:person.0615147542.17", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0615147542.17"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s10994-013-5335-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001526130", 
              "https://doi.org/10.1007/s10994-013-5335-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature12346", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019338075", 
              "https://doi.org/10.1038/nature12346"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/323533a0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018367015", 
              "https://doi.org/10.1038/323533a0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11957959_10", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014409254", 
              "https://doi.org/10.1007/11957959_10"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature14236", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030517994", 
              "https://doi.org/10.1038/nature14236"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2015-05-27", 
        "datePublishedReg": "2015-05-27", 
        "description": "Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.", 
        "genre": "article", 
        "id": "sg:pub.10.1038/nature14539", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1018957", 
            "issn": [
              "0028-0836", 
              "1476-4687"
            ], 
            "name": "Nature", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "7553", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "521"
          }
        ], 
        "keywords": [
          "deep learning", 
          "visual object recognition", 
          "multiple processing layers", 
          "Deep Convolutional Nets", 
          "representation of data", 
          "large data sets", 
          "convolutional nets", 
          "processing layer", 
          "speech recognition", 
          "sequential data", 
          "object recognition", 
          "backpropagation algorithm", 
          "recurrent nets", 
          "previous layer", 
          "computational model", 
          "data sets", 
          "speech", 
          "multiple levels", 
          "learning", 
          "internal parameters", 
          "representation", 
          "recognition", 
          "audio", 
          "nets", 
          "video", 
          "machine", 
          "algorithm", 
          "abstraction", 
          "images", 
          "discovers", 
          "set", 
          "text", 
          "art", 
          "data", 
          "detection", 
          "domain", 
          "discovery", 
          "drug discovery", 
          "model", 
          "method", 
          "breakthrough", 
          "layer", 
          "state", 
          "levels", 
          "parameters", 
          "light", 
          "genomics", 
          "structure"
        ], 
        "name": "Deep learning", 
        "pagination": "436-444", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1010020120"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1038/nature14539"
            ]
          }, 
          {
            "name": "pubmed_id", 
            "type": "PropertyValue", 
            "value": [
              "26017442"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1038/nature14539", 
          "https://app.dimensions.ai/details/publication/pub.1010020120"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-11-24T21:00", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221124/entities/gbq_results/article/article_659.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1038/nature14539"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1038/nature14539'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1038/nature14539'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/nature14539'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/nature14539'


     

    This table displays all metadata directly associated to this object as RDF triples.

    183 TRIPLES      21 PREDICATES      86 URIs      70 LITERALS      12 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1038/nature14539 schema:about N210c7d4c8a8d45a7bf16b72210308d6d
    2 N6a69443aada746279a71eb7a7f0712bc
    3 Nbdebbf8338534d4fa6043c4bceb0b39d
    4 Ne60415faf0ed4339819eb00fbb2c8e81
    5 Nf39afd5155f248b78160858d3aacb3c3
    6 anzsrc-for:08
    7 anzsrc-for:0801
    8 anzsrc-for:17
    9 anzsrc-for:1701
    10 anzsrc-for:1702
    11 schema:author N910614a36c41498b99253a8020e53ca9
    12 schema:citation sg:pub.10.1007/11957959_10
    13 sg:pub.10.1007/s10994-013-5335-x
    14 sg:pub.10.1038/323533a0
    15 sg:pub.10.1038/nature12346
    16 sg:pub.10.1038/nature14236
    17 schema:datePublished 2015-05-27
    18 schema:datePublishedReg 2015-05-27
    19 schema:description Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
    20 schema:genre article
    21 schema:isAccessibleForFree false
    22 schema:isPartOf N096f9647a65c46cebb2ee361bee15f01
    23 N24f081c2ee054fc39fb7cd8eb70d1077
    24 sg:journal.1018957
    25 schema:keywords Deep Convolutional Nets
    26 abstraction
    27 algorithm
    28 art
    29 audio
    30 backpropagation algorithm
    31 breakthrough
    32 computational model
    33 convolutional nets
    34 data
    35 data sets
    36 deep learning
    37 detection
    38 discovers
    39 discovery
    40 domain
    41 drug discovery
    42 genomics
    43 images
    44 internal parameters
    45 large data sets
    46 layer
    47 learning
    48 levels
    49 light
    50 machine
    51 method
    52 model
    53 multiple levels
    54 multiple processing layers
    55 nets
    56 object recognition
    57 parameters
    58 previous layer
    59 processing layer
    60 recognition
    61 recurrent nets
    62 representation
    63 representation of data
    64 sequential data
    65 set
    66 speech
    67 speech recognition
    68 state
    69 structure
    70 text
    71 video
    72 visual object recognition
    73 schema:name Deep learning
    74 schema:pagination 436-444
    75 schema:productId N80d1a8cc2a364402a38edecd73dc103f
    76 N91900f4060684a708f2ae8f66db95dc3
    77 Nac9763ba486d4e00acd7340a3d2afd8d
    78 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010020120
    79 https://doi.org/10.1038/nature14539
    80 schema:sdDatePublished 2022-11-24T21:00
    81 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    82 schema:sdPublisher N3b32e2bbe9e84e04bc7d6f0a77055a90
    83 schema:url https://doi.org/10.1038/nature14539
    84 sgo:license sg:explorer/license/
    85 sgo:sdDataset articles
    86 rdf:type schema:ScholarlyArticle
    87 N096f9647a65c46cebb2ee361bee15f01 schema:issueNumber 7553
    88 rdf:type schema:PublicationIssue
    89 N210c7d4c8a8d45a7bf16b72210308d6d schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    90 schema:name Artificial Intelligence
    91 rdf:type schema:DefinedTerm
    92 N24f081c2ee054fc39fb7cd8eb70d1077 schema:volumeNumber 521
    93 rdf:type schema:PublicationVolume
    94 N3b32e2bbe9e84e04bc7d6f0a77055a90 schema:name Springer Nature - SN SciGraph project
    95 rdf:type schema:Organization
    96 N6a69443aada746279a71eb7a7f0712bc schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    97 schema:name Computers
    98 rdf:type schema:DefinedTerm
    99 N80d1a8cc2a364402a38edecd73dc103f schema:name doi
    100 schema:value 10.1038/nature14539
    101 rdf:type schema:PropertyValue
    102 N8840f3f6b30a4646a743196a1fde55bc rdf:first sg:person.0615147542.17
    103 rdf:rest rdf:nil
    104 N910614a36c41498b99253a8020e53ca9 rdf:first sg:person.0765036655.42
    105 rdf:rest N956a8e1e73d745369bd04585099c10ca
    106 N91900f4060684a708f2ae8f66db95dc3 schema:name dimensions_id
    107 schema:value pub.1010020120
    108 rdf:type schema:PropertyValue
    109 N956a8e1e73d745369bd04585099c10ca rdf:first sg:person.01303456133.13
    110 rdf:rest N8840f3f6b30a4646a743196a1fde55bc
    111 Nac9763ba486d4e00acd7340a3d2afd8d schema:name pubmed_id
    112 schema:value 26017442
    113 rdf:type schema:PropertyValue
    114 Nbdebbf8338534d4fa6043c4bceb0b39d schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    115 schema:name Language
    116 rdf:type schema:DefinedTerm
    117 Ne60415faf0ed4339819eb00fbb2c8e81 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    118 schema:name Algorithms
    119 rdf:type schema:DefinedTerm
    120 Nf39afd5155f248b78160858d3aacb3c3 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
    121 schema:name Neural Networks, Computer
    122 rdf:type schema:DefinedTerm
    123 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    124 schema:name Information and Computing Sciences
    125 rdf:type schema:DefinedTerm
    126 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    127 schema:name Artificial Intelligence and Image Processing
    128 rdf:type schema:DefinedTerm
    129 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
    130 schema:name Psychology and Cognitive Sciences
    131 rdf:type schema:DefinedTerm
    132 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
    133 schema:name Psychology
    134 rdf:type schema:DefinedTerm
    135 anzsrc-for:1702 schema:inDefinedTermSet anzsrc-for:
    136 schema:name Cognitive Sciences
    137 rdf:type schema:DefinedTerm
    138 sg:journal.1018957 schema:issn 0028-0836
    139 1476-4687
    140 schema:name Nature
    141 schema:publisher Springer Nature
    142 rdf:type schema:Periodical
    143 sg:person.01303456133.13 schema:affiliation grid-institutes:grid.14848.31
    144 schema:familyName Bengio
    145 schema:givenName Yoshua
    146 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01303456133.13
    147 rdf:type schema:Person
    148 sg:person.0615147542.17 schema:affiliation grid-institutes:grid.17063.33
    149 schema:familyName Hinton
    150 schema:givenName Geoffrey
    151 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0615147542.17
    152 rdf:type schema:Person
    153 sg:person.0765036655.42 schema:affiliation grid-institutes:grid.137628.9
    154 schema:familyName LeCun
    155 schema:givenName Yann
    156 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0765036655.42
    157 rdf:type schema:Person
    158 sg:pub.10.1007/11957959_10 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014409254
    159 https://doi.org/10.1007/11957959_10
    160 rdf:type schema:CreativeWork
    161 sg:pub.10.1007/s10994-013-5335-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1001526130
    162 https://doi.org/10.1007/s10994-013-5335-x
    163 rdf:type schema:CreativeWork
    164 sg:pub.10.1038/323533a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018367015
    165 https://doi.org/10.1038/323533a0
    166 rdf:type schema:CreativeWork
    167 sg:pub.10.1038/nature12346 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019338075
    168 https://doi.org/10.1038/nature12346
    169 rdf:type schema:CreativeWork
    170 sg:pub.10.1038/nature14236 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030517994
    171 https://doi.org/10.1038/nature14236
    172 rdf:type schema:CreativeWork
    173 grid-institutes:grid.137628.9 schema:alternateName New York University, 715 Broadway, 10003, New York, New York, USA
    174 schema:name Facebook AI Research, 770 Broadway, 10003, New York, New York, USA
    175 New York University, 715 Broadway, 10003, New York, New York, USA
    176 rdf:type schema:Organization
    177 grid-institutes:grid.14848.31 schema:alternateName Department of Computer Science and Operations Research Université de Montréal, Pavillon André-Aisenstadt, PO Box 6128 Centre-Ville STN, H3C 3J7, Montréal, Quebec, Canada
    178 schema:name Department of Computer Science and Operations Research Université de Montréal, Pavillon André-Aisenstadt, PO Box 6128 Centre-Ville STN, H3C 3J7, Montréal, Quebec, Canada
    179 rdf:type schema:Organization
    180 grid-institutes:grid.17063.33 schema:alternateName Department of Computer Science, University of Toronto, 6 King's College Road, M5S 3G4, Toronto, Ontario, Canada
    181 schema:name Department of Computer Science, University of Toronto, 6 King's College Road, M5S 3G4, Toronto, Ontario, Canada
    182 Google, 1600 Amphitheatre Parkway, 94043, Mountain View, California, USA
    183 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...