Science Explorer Back to mapMap
Discussion
Researcher · New York University · United States

Yann LeCun

Yann LeCun publishes mostly in Computer Vision and Pattern Recognition, Artificial Intelligence and Signal Processing, on topics such as Domain Adaptation and Few-Shot Learning, Neural Networks and Applications and Advanced Image and Video Retrieval Techniques.

ORCID 0000-0002-1992-2684 OpenAlex
World rank
#5,773
of 7,710,434 ranked researchers
Rank in United States
#1,992
of 1,627,098
Works
470
Citations
256k
Citations per work
545.1
h-index
119
i10-index 278Top 0.1% in Computer Vision and Pattern Recognition
Yann LeCun

What does Yann LeCun research?

Yann LeCun's work is mostly in Computer Science (73%), Engineering (4%), Neuroscience (2%).

Physical Sciences: 362 works · 77.1% of their workComputer Science: 345 works · 73.4% of their workComputer Vision and Pattern Recognition: 170 works · 36.2% of their workArtificial Intelligence: 152 works · 32.4% of their workSignal Processing: 23 works · 4.8% of their workEngineering: 17 works · 3.7% of their workElectrical and Electronic Engineering: 9 works · 1.9% of their workMedia Technology: 8 works · 1.8% of their workEverything else: 100 works · 21.2% of their workLife Sciences: 8 works · 1.7% of their workNeuroscience: 8 works · 1.7% of their workCognitive Neuroscience: 8 works · 1.7% of their workTHEIR WORKYann LeCun470works
Life Sciences2%Physical Sciences77%

Their six largest subfields, inside their fields and domains; the grey slice is everything else they publish. The interactive view splits every one of their works down to single topics.

The fields and subfields, with their numbers
    1. Computer Science34573.4%
    2. Engineering173.7%
  2. Everything else10021.2%
    1. Neuroscience81.7%
  1. 1Computer Vision and Pattern Recognition36% of their works
  2. 2Artificial Intelligence32% of their works
  3. 3Signal Processing5% of their works
  4. 4Electrical and Electronic Engineering2% of their works
  5. 5Media Technology2% of their works
  6. 6Cognitive Neuroscience2% of their works

Research topics

Which keywords describe Yann LeCun's research?

The keywords of their largest research topics: Deep Learning, Neural Networks, Representation Learning, Unsupervised Learning, Domain Adaptation, Transfer Learning, Backpropagation Learning and Self-Organizing Maps.

Size is their works in the topics tagged with each word, from their 8 largest topics. Each links to the topic it comes from most.

All 20 words, with their numbers
  1. Deep Learning2595 topics
  2. Neural Networks1844 topics
  3. Representation Learning1182 topics
  4. Unsupervised Learning1182 topics
  5. Domain Adaptation751 topic
  6. Transfer Learning751 topic
  7. Backpropagation Learning741 topic
  8. Self-Organizing Maps741 topic
  9. Feature Matching571 topic
  10. Local Descriptors571 topic
  11. Convolutional Neural Networks511 topic
  12. Image Recognition511 topic
  13. Generative Adversarial Networks431 topic
  14. Image Synthesis431 topic
  15. Image Captioning341 topic
  16. Visual Question Answering341 topic
  17. Machine Translation331 topic
  18. Word Representation331 topic
  19. Content-Based Image Retrieval301 topic
  20. Shape Matching301 topic

Where does Yann LeCun work?

Yann LeCun's main affiliation in the publication record is New York University, United States.

How many publications and citations does Yann LeCun have?

OpenAlex counts 470 works and 256,177 citations for Yann LeCun, an h-index of 119, ranking #5,773 of 7,710,434 researchers worldwide on the quality score.

Ranked on field-normalised excellence (50%), output (30%) and citations (20%). Counts come from OpenAlex author records, which occasionally merge different people who share a name or split one person into several.

Other researchers named Yann LeCun

Papers, co-authors, who cited this work and researchers on the nearest topics have tabs of their own, above. Is this your page? Claim it with your ORCID iD, or request a correction or removal.

Discussion

Ask a question or share a note about Yann LeCun. Posts are plain text and can be reported.