ABCDEFGHIJKLMNOPQRSTUVWXYZAAABACAD
1
SystemDomainTaskOrganization(s)
Organization Categorization
Author(s)
Publication date
YearReferenceLinkCitations
Inclusion criteria
Inclusion criteria met
Parameters
Training compute (FLOPs)
Training dataset
Training dataset size (datapoints)
Hidden layers
Inference compute (FLOPs)
Training time (hours)
Equivalent training time (hours)
Inference time (ms)Training dataset size (GB)ApproachDense or sparse modelTraining objectiveTraining cost (2020 USD)Self-supervised trainingArchitecture
Compute Sponsor Categorization
2
TheseusOtherMaze solvingBell LaboratoriesIndustry
Claude Shannon
02/07/19501950Mighty Mouse
https://www.technologyreview.com/2018/12/19/138508/mighty-mouse/
N/A
Historical relevance
Yes4.00E+014.00E+014.00E+01Industry
3
SNARCOtherMaze solving
Harvard University Psychological Laboratories
Academia
Marvin Minsky
08/01/19521952
A Neural-Analogue Calculator Based upon a Probability Model of Reinforcement
https://en.wikipedia.org/wiki/Stochastic_neural_analog_reinforcement_calculator
3.30E+01
Historical relevance
Yes4.00E+01Academia
4
Institute for Advanced Study
AcademiaNA Barricelli02/07/19541954
Esempi numerici di processi di evoluzione
https://link.springer.com/article/10.1007/BF01556771
2.66E+02
Historical relevance
YesAcademia
5
Self Organizing SystemVision
Pattern recognition
Massachusetts Institute of Technology
Academia
W. A. Clark and B. G. Farley
01/03/19551955
Generalization of pattern recognition in a self-organizing system
https://dl.acm.org/doi/10.1145/1455292.1455309
8.30E+01
Historical relevance
Yes2.25E+022.56E+02Academia
6
Vision
Character recognition
Massachusetts Institute of Technology
Academia
O. G. Selfridge
01/03/19551955
Pattern recognition and learning
https://dl.acm.org/doi/10.1145/1455292.1455310
2.90E+02
Historical relevance
YesAcademia
7
VisionPrinceton UniversityAcademiaAM Uttley01/07/19561956
Conditional probability machines
https://www.moma.org/collection/works/illustratedbooks/16252?locale=es
8.40E+01
Historical relevance
YesAcademia
8
Perceptron Mark IVision
Binary classification
Cornell Aeronautical Laboratory
IndustryF Rosenblatt01/01/19571957
The Perceptron—a perceiving and recognizing automaton
https://blogs.umass.edu/brain-wars/files/2016/03/rosenblatt-1957.pdf
1.61E+03
Historical relevance
Yes4.00E+026.95E+056.00E+00N/AN/AN/AIndustry
9
Pandemonium (morse)Other
Morse translation
Massachusetts Institute of Technology
AcademiaOG Selfridge01/02/19591959
Pandemonium: A Paradigm for Learning
https://aitopics.org/doc/classics:504E1BAC/
1.45E+03Highly citedYes3.00E+036.00E+08Academia
10
Samuel Neural CheckersGamesCheckersIBMIndustry
Arthur L. Samuel
01/07/19591959
Some studies in machine learning using the game of checkers
https://ieeexplore.ieee.org/abstract/document/5392560
4.15E+03Highly citedYes1.60E+014.28E+085.30E+04N/A97.5Industry
11
Vision
Character recognition
Sandia CorporationIndustry
W. W. Bledsoe, I. Browning
01/12/19591959
Pattern recognition and reading by machine
https://www.computer.org/csdl/proceedings-article/afips/1959/50550225/12OmNqN6R43
5.53E+02
Historical relevance
Yes2.63E+03Industry
12
ADALINEVision
Pattern recognition
Standford UniversityAcademia
Widrow and Hoff
30/06/19601960
Adaptive switching circuits
https://isl.stanford.edu/~widrow/papers/c1960adaptiveswitching.pdf
6.33E+03Highly citedYes1.70E+019.90E+031.00E+023.30E+01Academia
13
LMSStandford UniversityAcademia
Widrow and Hoff
30/06/19601960
Adaptive switching circuits (technical report)
https://www.scirp.org/(S(351jmbntvnsjt1aadkposzje))/reference/ReferencesPapers.aspx?ReferenceID=547230
6.33E+03Highly citedYesAcademia
14
Massachusetts Institute of Technology (MIT)
Academia
Marvin Minsky
01/01/19611961
Steps Toward Artificial Intelligence
https://ieeexplore.ieee.org/abstract/document/4066245
2.43E+03Highly citedYesAcademia
15
Massachusetts Institute of Technology (MIT)
Academia
Marvin Minsky and Oliver G. Selfridge
01/07/19611961
Learning in random nets
https://stacks.stanford.edu/file/druid:yr384hg3073/yr384hg3073.pdf
4.70E+01
Historical relevance
YesAcademia
16
Binary classification
The University of GenoaAcademia
A Gamba, L Gamberini, G Palmieri, R Sanna
01/09/19611961
Further experiments with PAPA
https://www.semanticscholar.org/paper/Further-experiments-with-PAPA-Gamba-Gamberini/c3a20b9aa86033cec29f08e69f4bc81e8b329ae2
2.10E+01YesAcademia
17
MADALINE IStandford UniversityAcademia
William Combs Ridgway
01/07/19621962
An adaptive logic system with generalizing properties
https://www.proquest.com/openview/7898314db50a218b58052ac91e3bde1e/1?
7.50E+01
Historical relevance
YesAcademia
18
STeLLAUniversity of CanterburyAcademia
J.H. Andreae and Peter L. Joyce
01/06/19631963
STeLLA: A Scheme for a Learning Machine
https://www.researchgate.net/publication/252919025_STELLA_A_scheme_for_a_learning_machine
3.40E+01YesAcademia
19
MENACEGamesTic Tac ToeUniversity of EdinburghAcademia
University of Edinburgh
01/11/19631963
Experiments on the Mechanization of Game-Learning Part I. Characterization of the Model and its parameters
https://academic.oup.com/comjnl/article/6/3/232/360077
4.60E+01YesAcademia
20
Samuel Neural Checkers II
GamesCheckersUniversity of GenevaAcademia
Palmieri, G. and R. Sanna
01/11/19671967
Some studies in machine learning using the game of checkers. Part II
https://www.cs.virginia.edu/~evans/greatworks/samuel.pdf
7.47E+02Yes4.00E+01N/AAcademia
21
GLEEGamesTic Tac ToeUniversity of EdinburghAcademia
Michie and Chambers
01/07/19681968
Boxes: An Experiment in Adaptive Control
https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.474.2430
5.90E+02
Historical relevance
YesAcademia
22
BOXESGamesPole balancingUniversity of EdinburghAcademia
Michie and Chambers
01/07/19681968
Boxes: An Experiment in Adaptive Control
https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.474.2430
5.90E+02
Historical relevance
YesAcademia
23
Massachusetts Institute of Technology
Academia
Patrick Winston
01/09/19701970
Learning Structural Definitions from Examples
https://dspace.mit.edu/handle/1721.1/6884
1.81E+03Highly citedYesAcademia
24
Bootstrap AdaptationGamesBlackjackIEEEAcademia
Widrow, Gupta, and Maitra
01/09/19731973
Punish/Reward: Learning with a Critic in Adaptive Threshold Systems
https://ieeexplore.ieee.org/document/4309272
3.82E+02Yes2.10E+01Academia
25
Naive BayesVision
Massachusetts Institute of Technology
Industry
Duda and Hart
01/09/19741974
Pattern Classification and Scene Analysis
https://www.semanticscholar.org/paper/Pattern-classification-and-scene-analysis-Duda-Hart/b07ce649d6f6eb636872527104b0209d3edc8188
2.31E+04Highly citedYesIndustry
26
CognitronBiological CyberneticsIndustry
Kunihiko Fukushima
01/09/19751975
Cognitron: a self-organizing multilayered neural network
https://link.springer.com/article/10.1007%2FBF00342633
7.91E+02
Historical relevance
YesIndustry
27
TD(0)University of EssexAcademiaIan Witten01/08/19771977
An adaptive optimal controller for discrete-time Markov environments
https://www.sciencedirect.com/science/article/pii/S0019995877903540
2.44E+02
Historical relevance
YesAcademia
28
VisionUtrecht UniversityAcademia
Koenderink & van Doom
02/05/19791979
The internal representation of solid shape with respect to vision
https://link.springer.com/article/10.1007/BF00337644
9.81E+02
Historical relevance
YesAcademia
29
NeocognitronVision
Character recognition
NHK Broadcasting Science Research Laboratories
Industry
K Fukushima, S Miyake
01/04/19801980
Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
https://link.springer.com/article/10.1007/BF00344251
5.78E+03Highly citedYes1.14E+062.28E+085.00E+00Industry
30
Kohonen networkOther
Dimensionality reduction
Helsinki University of Technology
AcademiaT Kohonen25/07/19811981
Self-organized formation of topologically correct feature maps
https://link.springer.com/article/10.1007/BF00337288
1.18E+04Highly citedYes4.10E+03Academia
31
Hopfield networkOther
Sequence memorization
California Institute of Technology
AcademiaJJ Hopfield01/04/19821982
Neural networks and physical systems with emergent collective computational abilities
https://www.pnas.org/doi/10.1073/pnas.79.8.2554
2.33E+04Highly citedYes9.90E+03N/AAcademia
32
ASE+ACEGamesPole balancingStanfordAcademia
Andrew G. Barto, Richard S. Sutton, and Charles W. Anderson
01/09/19831983
Neuronlike adaptive elements that can solve difficult learning control problems
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6313077
4.30E+03Highly citedYes3.24E+02Academia
33
LanguageMITAcademia
Steven Pinker
01/07/19841984
Language learnability and language development.
https://psycnet.apa.org/record/1985-97439-000
4.73E+03Highly citedYesAcademia
34
University of California and University of Carnegie Mellon
Academia
D. E. Rumelhart, G. E. Hinton, and R. J. Williams
03/01/19861986
Learning internal representations by error propagation
https://dl.acm.org/doi/10.5555/104279.104293
2.73E+04Highly citedYesAcademia
35
Language
Verb conjugation
StanfordAcademia
Rumelhart, D. E., & McClelland, J. L
03/01/19861986
Learning the past tenses of English verbs: Implicit rules or parallel distributed processing?
https://www.semanticscholar.org/paper/On-learning-the-past-tenses-of-English-verbs%3A-rules-Rumelhart-McClelland/4fa569625b5ab35e955a8d5be11a4aa9f59ca424
3.06E+02Yes2.12E+05
Parallel Distributed Processing Model
Industry
36
University of CaliforniaAcademiaJordan, M.I.05/01/19861986
Serial order: A parallel distributed processing approach
https://www.osti.gov/biblio/6910294
1.50E+03Highly citedYesAcademia
37
Back-propagationOther
Learning to complete triples
University of CaliforniaAcademia
Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J.
01/10/19861986
Learning representations by back-propagating errors
https://www.semanticscholar.org/paper/Learning-representations-by-back-propagating-errors-Rumelhart-Hinton/052b1d8ce63b07fec3de9dbb583772d860b7c769
2.53E+04Highly citedYes1.44E+021.24E+081.44E+022.88E+02UnsupervisedAcademia
38
Vision
Massachusetts Institute of Technology
AcademiaJohn Canny01/11/19861986
A Computational Approach To Edge Detection
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4767851
3.79E+04Highly citedYesAcademia
39
Vision
University of California, Santa Cruz
Academia
Biederman, Irving
01/04/19871987
Recognition-by-components: A theory of human image understanding
https://psycnet.apa.org/record/1987-20898-001
7.59E+03Highly citedYesAcademia
40
NetTalkSpeech
Speech synthesis
Princeton UniversityAcademia
TJ Sejnowski, CR Rosenberg
06/06/19871987
Parallel Networks that Learn to Pronounce English Text
http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=03A3D3EDF0BAF35405ABCF083411B55E?doi=10.1.1.154.7012&rep=rep1&type=pdf
2.56E+03Highly citedYes1.86E+048.12E+102.10E+041Academia
41
VisionRoke Manor ResearchIndustry
Harris & Stephens
01/07/19881988
A Combined Corner and Edge Detector
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.434.4816&rep=rep1&type=pdf
1.91E+04Highly citedYes1.50E+03Industry
42
MADALINE IIOther
Pattern classification
Stanford UniversityAcademia
Rodney Winter, Bernard Widrow
24/07/19881988
MADALINE RULE II: A Training Algorithm for Neural Networks
https://ieeexplore.ieee.org/document/23872
8.10E+01YesAcademia
43
Adaptive Broom BalancerGamesPole balancingStanford UniversityAcademia
VV Tolat, B Widrow
24/07/19881988
An Adaptive “Broom Balancer” with Visual Inputs
https://ieeexplore.ieee.org/document/23982
8.00E+01Yes1.10E+02Academia
44
Q-learningUniversity of LondonAcademia
Christopher Watkins
01/01/19891989
Learning from delayed rewards
http://www.cs.rhul.ac.uk/~chrisw/thesis.html
8.03E+03Highly citedYesAcademia
45
Time-delay neural networks
Carnegie Mellon University & ATR Interpreting Telephony Research Laboratories & University of Toronto
Industry - Academia Collaboration
A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, and K. J. Lang
03/03/19891989
Phoneme recognition using time-delay neural networks
https://ieeexplore.ieee.org/abstract/document/21701
3.45E+03Highly citedYesIndustry
46
Technische Universität Wien Austria & University of California
Academia
Kurt Hornik & Maxwell Stinchcombe & Halbert White
09/03/19891989
Multilayer feedforward networks are universal approximators
https://www.sciencedirect.com/science/article/abs/pii/0893608089900208
2.17E+04Highly citedYesAcademia
47
ALVINNDriving
Carnegie Mellon University
Academia
DA Pomerleau
01/12/19891989
ALVINN: an autonomous land vehicle in a neural network
https://proceedings.neurips.cc/paper/1988/hash/812b4ba287f5ee0bc9d43bbf5bbe87fb-Abstract.html
1.58E+03Highly citedYes3.99E+038.12E+10
Road snapshots
1.20E+031Academia
48
Zip CNNVision
Character recognition
AT&T Bell LaboratoriesIndustry
Y. LeCun B. Boser J. S. Denker D. Henderson R. E. Howard W. Hubbard L. D. Jackel
01/12/19891989
Backpropagation applied to handwritten zip code recognition
https://ieeexplore.ieee.org/document/6795724
9.05E+03Highly citedYes9.76E+034.34E+10
Buffalo zips
7.29E+0331.29E+05Industry
49
MADALINE IIIUniversity of StanfordAcademia
B Widrow, M. A. Lehr
01/09/19901990
30 years of adaptive neural networks: perceptron, madaline, and backpropagation
https://ieeexplore.ieee.org/document/58323
3.01E+03YesAcademia
50
Air Force Institute of Technology, OH, USA
Academia
D.W. Ruck & S.K. Rogers & M. Kabrisky & M.E. Oxley & B.W. Suter
01/12/19901990
The multilayer perceptron as an approximation to a Bayes optimal discriminant function
https://ieeexplore.ieee.org/abstract/document/80266
1.05E+03Highly citedYesAcademia
51
DIABETESOther
Medical diagnosis
Aalborg UniversityAcademia
S. Andreassen, R. Hovorka, J. Benn, K. G. Olesen, and E. R. Carson
24/06/19911991
A Model-based Approach to Insulin Adjustment
https://link.springer.com/chapter/10.1007/978-3-642-48650-0_19
1.32E+02Yes4.29E+05Academia
52
Language
University of California, San Diego
AcademiaJ. L. Elman01/09/19911991
Distributed representations, simple recurrent networks, and grammatical structure
https://dl.acm.org/doi/10.1007/BF00114844
1.72E+03Highly citedYes1.78E+05
Recurrent Network ("Elman" network?)
Academia
53
Northeastern UniversityAcademiaR. J. Williams01/05/19921992
Simple statistical gradient-following algorithms for connectionist reinforcement learning
https://dl.acm.org/doi/10.1007/BF00992696
6.53E+03Highly citedYesAcademia
54
TD-GammonGamesBackgammonIBMIndustryG Tesauro01/05/19921992
Practical Issues in Temporal Difference Learning
https://papers.nips.cc/paper/1991/file/68ce199ec2c5517597ce0a4d89620f55-Paper.pdf
1.34E+03Highly citedYes2.50E+041.82E+136.30E+061Industry
55
Fuzzy NNSpeech
Speech recognition
Indian Statistical InstituteAcademia
SK Pal, S Mitra
01/09/19921992
Multilayer perceptron, fuzzy sets, and classification
https://ieeexplore.ieee.org/document/159058
1.22E+03Highly citedYes1.17E+033.05E+068.71E+02Academia
56
IBM-5LanguageTranslation
IBM T.J. Watson Research Center
Industry
Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, Robert L. Mercer
15/06/19931993
The Mathematics of Statistical Machine Translation: Parameter Estimation
https://dl.acm.org/doi/10.5555/972470.972474
5.75E+03Highly citedYes1.66E+06
Proceedings of the Canadian parliament
5.34E+07Statistical Alignment ModelIndustry
57
Language
Part-of-speech tagging
EURECOMAcademia
Bernard Merialdo
01/06/19941994
Tagging English Text with a Probabilistic Model
https://dl.acm.org/doi/10.5555/972525.972526
7.88E+02Yes2.45E+061.00E+06N/AAcademia
58
GroupLens
Recommendation
Massachusetts Institute of Technology
Academia
Paul Resnick, Neophytos Iacovou, Mitesh Suchak, Peter Bergstrom, John Riedl
22/10/19941994
GroupLens : an Open Architecture for Collaborative Filtering of Netnews
https://dl.acm.org/doi/10.1145/192844.192905
7.73E+03Highly citedYes1.00E+081.00E+08Academia
59
XeroxIndustryEric Saund01/01/19951995
A Multiple Cause Mixture Model for Unsupervised Learning
https://ieeexplore.ieee.org/document/6795568
1.76E+02YesPerplexity... sortaIndustry
60
Language
University of Pennsylvania
AcademiaD Yarowsky26/06/19951995
Unsupervised Word Sense Disambiguation Rivaling Supervised Methods
https://dl.acm.org/doi/10.3115/981658.981684
3.00E+03Highly citedYes4.60E+08Bootstrapping classifierAcademia
61
Random Decision Forests
AT&T Bell LaboratoriesIndustryTK Ho14/08/19951995
Random decision forests
https://ieeexplore.ieee.org/document/598994
4.68E+03Highly citedYesMNIST6.00E+04Industry
62
Support Vector MachinesAT&T Bell LaboratoriesIndustry
C Cortes, V Vapnik
01/09/19951995
Support-Vector Networks
https://link.springer.com/article/10.1007/BF00994018
4.90E+04Highly citedYes1.00E+08MNIST6.00E+04Industry
63
System 11VisionFace recognition
Carnegie Mellon University
Academia
HA Rowley, S Baluja, T Kanade
18/06/19961996
Neural Network-Based Face Detection
https://ieeexplore.ieee.org/document/655647
6.01E+03Highly citedYes6.45E+039.58E+089.05E+031.29E+04Academia
64
HMM Word AlignmentLanguageWord alignment
University of Erlangen - Nuremburg
Academia
Stephan Vogel, Hermann Ney, Christoph Tillmann
05/08/19961996
HMM-Based Word Alignment in Statistical Translation
https://dl.acm.org/doi/10.3115/993268.993313
1.10E+03Highly citedYes4.42E+05SupervisedStatistical Alignment ModelAcademia
65
VisionMITAcademia
E. Osuna, R. Freund, F. Girosi
17/06/19971997
Training Support Vector Machines: An Application to Face Detection
https://ieeexplore.ieee.org/document/609310
3.85E+03Highly citedYes5.00E+04Academia
66
Language
Cambridge University Engineering & Carnegie Mellon University
Academia
P Clarkson, R Rosenfeld
01/07/19971997
Statistical language modeling using the CMU-Cambridge toolkit
https://www.semanticscholar.org/paper/Statistical-language-modeling-using-the-toolkit-Clarkson-Rosenfeld/fdf4aa623e4d5b5edaeb873ed8e8b1cef0b59c87
9.54E+02YesSupervisedAcademia
67
BRNNSpeech
Speech recognition
ATR Labs, JapanIndustry
M. Schuster, KK Paliwal
01/11/19971997
Bidirectional recurrent neural networks
https://ieeexplore.ieee.org/document/650093
6.09E+03Highly citedYes1.30E+04TIMIT7.39E+04Industry
68
LSTMOther
Sequence recognition (?)
The Technical University of Munich
Academia
Sepp Hochreiter ; Jurgen Schmidhuber
15/11/19971997
Long short-term memory
https://direct.mit.edu/neco/article-abstract/9/8/1735/6109/Long-Short-Term-Memory?redirectedFrom=fulltext
5.20E+04Highly citedYes1.05E+042.10E+131.27E+064.20E+04Academia
69
UC Davis, CornellAcademia
Bruno A. Olshausen, David J. Field
01/12/19971997
Sparse coding with an overcomplete basis set: A strategy employed by V1?
https://www.sciencedirect.com/science/article/pii/S0042698997001697
4.26E+03Highly citedYes1.00E+01Academia
70
Speech
Johns Hopkins University
AcademiaF Jelinek15/01/19981998
Statistical Methods for Speech Recognition
https://mitpress.mit.edu/books/statistical-methods-speech-recognition
3.06E+03Highly citedYesAcademia
71
RNN for speechSpeech
Speech synthesis
National Chiao Tung University
Academia
SH Chen, SH Hwang, YR Wang
15/05/19981998
An RNN-based prosodic information synthesizer for Mandarin text-to-speech
https://ieeexplore.ieee.org/abstract/document/668817
2.31E+02Yes7.51E+032.27E+111.41E+04Academia
72
VisionFace recognition
Carnegie Mellon University
Academia
H Schneiderman, T Kanade
23/06/19981998
Probabilistic modeling of local appearance and spatial relationships for object recognition
https://ieeexplore.ieee.org/document/698586
6.02E+02Yes1.20E+05Academia
73
Other
Recommender system
AT&T Labs and Rutgers University and Bell Communications Research
Industry - Academia Collaboration
C Basu, H Hirsh, W Cohen
01/07/19981998
Recommendation as Classification : Using Social and Content-based Information in Recommendation
https://www.aaai.org/Papers/AAAI/1998/AAAI98-101.pdf
1.56E+03Highly citedYes4.50E+04Industry
74
LeNet-5Vision
Character recognition
AT&T Labs
Industry - Academia Collaboration (Industry leaning)
Yann LeCun, Léon Bottou, Yoshua Bengio, Patrick Haffner
01/11/19981998
Gradient-based Learning Applied to Document Recognition
http://vision.stanford.edu/cs598_spring07/papers/Lecun98.pdf
3.86E+04
Historical relevance
Yes6.00E+042.81E+12MNIST6.00E+0467.81E+050.021Industry
75
IDSIA SwitzerlandAcademia
F. A. Gers, J. Schmidhuber, and F. Cummins
02/01/19991999
Learning to forget: Continual prediction with LSTM
https://ieeexplore.ieee.org/document/818041
4.52E+03Highly citedYes2.76E+023.00E+04Academia
76
IBM Model 4LanguageTranslation
University of Southern California & IBM & University of Pennsylvania
Industry - Academia Collaboration (Academia leaning)
Yaser Al-Onaizan, Jan Curin, Michael Jahr, Kevin Knight, John Lafferty, Dan Melamed, Franz-Josef Och, David Purdy, Noah A. Smith, and David Yarowsky
02/07/19991999
Statistical machine translation
http://www-i6.informatik.rwth-aachen.de/publications/download/266/al-onaizan--1999.pdf
1.92E+03Highly citedYes8.00E+05Industry
77
Vision
Character recognition
University of California San Diego & Shannon Laboratory, AT&T Labs
Industry
Yoav Freund & Robert E. Schapire
01/12/19991999
Large Margin Classification Using the Perceptron Algorithm
https://link.springer.com/article/10.1023/A:1007662407062
1.73E+03Highly citedYesMNIST6.00E+04Industry
78
Recommendation
University of MinnesotaAcademia
B Sarwar, G Karypis, J Konstan, J Riedl
14/07/20002000
Application of Dimensionality Reduction in Recommender System -- A Case Study
http://robotics.stanford.edu/~ronnyk/WEBKDD2000/papers/sarwar.pdf
2.13E+03Highly citedYesAcademia
79
Peephole LSTMOther
Periodic function approximation
IDSIA SwitzerlandAcademia
F.A. Gers; J. Schmidhuber
26/07/20002000
Recurrent nets that time and count
https://ieeexplore.ieee.org/document/861302
6.30E+02Yes1.70E+016.50E+07Academia
80
LanguageUniversity of RochesterAcademia
Daniel Gildea, Daniel Jurafsky
01/09/20002000
Automatic Labeling of Semantic Roles
https://dl.acm.org/doi/10.1162/089120102760275983
2.33E+03Highly citedYesFrameNet5.00E+04Academia
81
Language
RWTH Aachen - University of Technology
Academia
Franz Josef Och, Hermann Ney
03/10/20002000
Improved Statistical Alignment Models
https://aclanthology.org/P00-1056/
1.32E+03Highly citedYesStatistical Alignment ModelAcademia
82
Immediate triheadLanguageBrown UniversityAcademiaE Charniak06/07/20012001
Immediate-Head Parsing for Language Models
https://dl.acm.org/doi/10.3115/1073012.1073029
4.22E+02YesAcademia
83
Standford UniversityAcademia
Jerome H. Friedman
01/10/20012001
Greedy function approximation: A gradient boosting machine
https://projecteuclid.org/journals/annals-of-statistics/volume-29/issue-5/Greedy-function-approximation-A-gradient-boostingmachine/10.1214/aos/1013203451.full
1.43E+04Highly citedYesAcademia
84
Decision tree (classification)
VisionFace recognition
Mitsubishi Electric Research Labs and Compaq CRL
Industry - Academia Collaboration
P. Viola, M. Jones
08/12/20012001
Rapid object detection using a boosted cascade of simple features
https://www.cs.cmu.edu/~efros/courses/LBMV07/Papers/viola-cvpr-01.pdf
2.34E+04Highly citedYes1.20E+086.30E+131.45E+046.70E+07Industry
85
Thumbs Up?Language
Sentiment classification
Cornell University and IBM Almaden Research Center
Industry - Academia Collaboration
Bo Pang, Lillian Lee, Shivakumar Vaithyanathan
28/05/20022002
Thumbs up? Sentiment Classification using Machine Learning Techniques
https://arxiv.org/abs/cs/0205070
1.07E+04Highly citedYesIMDb2.05E+03Industry
86
LanguageAT&T LabsIndustry
Michael Collins
01/06/20022002
Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms
https://dl.acm.org/doi/10.3115/1118693.1118694
2.58E+03Highly citedYesIndustry
87
Language
University of Southern California
Industry - Academia Collaboration
Daniel Marcu and William Wong
01/06/20022002
A Phrase-Based, Joint Probability Model for Statistical Machine Translation
https://dl.acm.org/doi/10.3115/1118693.1118711
6.23E+02Yes
Hansard Corpus
1.07E+06Statistical Alignment ModelIndustry
88
IDSIA SwitzerlandAcademia
Justin Bayer, Daan Wierstra, Julian Togelius, Jürgen Schmidhuber
01/06/20022002
Evolving Neural Networks through Augmenting Topologies
https://direct.mit.edu/evco/article/10/2/99/1123/Evolving-Neural-Networks-through-Augmenting
3.37E+03Highly citedYesAcademia
89
LanguageTranslation
RWTH Aachen and University of Southern California
Academia
Franz Josef Och and Hermann Ney
06/07/20022002
Discriminative Training and Maximum Entropy Models for Statistical Machine Translation
https://aclanthology.org/P02-1038/
1.41E+03Highly citedYes5.20E+05Academia
90
Language
IBM TJ Watson Research Centre
Industry
K Papineni, S Roukos, T Ward, WJ Zhu
06/07/20022002
Bleu: a method for automatic evaluation of machine translation
https://dl.acm.org/doi/10.3115/1073083.1073135
1.58E+04Highly citedYesIndustry
91
Korea Advanced Institute of Science and Technology
Academia
YH Cho, JK Kim, SH Kim
01/10/20022002
A personalized recommender system based on web usage mining and decision tree induction
https://reader.elsevier.com/reader/sd/pii/S0957417402000520?token=155B6D1937982D7D0271AFD1CFB034DFD7F3D1DE816B66C025EBC9D0A305BA6DA685DD62989DC05246C794CAC74CDAEF&originRegion=us-east-1&originCreation=20220325235441
6.56E+02YesAcademia
92
Recommendation
University of Washington
Industry - Academia Collaboration
G. Linden, B. Smith, and J. York
01/01/20032003
Amazon.com Recommendations: Item-to-Item Collaborative Filtering
https://ieeexplore.ieee.org/document/1167344
7.26E+03Highly citedYesIndustry
93
Vision
Image Classification
California Institute of Technology
Academia
M. Weber, M. Welling, and P. Perona
01/01/20032003
Unsupervised Learning of Models for Recognition
https://link.springer.com/content/pdf/10.1007/3-540-45054-8_2.pdf
Historical relevance
YesAcademia
94
LDALanguage
Document classification
University of California, Stanford University
Academia
David M. Blei, Andrew Y. Ng, Michael I. Jordan
02/02/20032003
Latent Dirichlet Allocation
https://jmlr.org/papers/volume3/blei03a/blei03a.pdf
3.87E+04Highly citedYes
Hierarchial Bayesian Model/Generative Probabilistic Model
Academia
95
NPLMLanguage
Text autocompletion
Université de MontréalAcademia
Yoshua Bengio, Réjean Ducharme, Pascal Vincent, Christian Jauvin
15/03/20032003
A Neural Probabilistic Language Model
https://dl.acm.org/doi/10.5555/944919.944966
7.63E+03Highly citedYes1.19E+071.30E+15
Brown corpus
1.00E+062.17E+0720160Academia
96
Phrase-based translationLanguageTranslation
University of Southern California
Academia
Philipp Koehn, Franz Josef Och, Daniel Marcu
01/05/20032003
Statistical Phrase-Based Translation
https://dl.acm.org/doi/10.3115/1073445.1073462
4.27E+03Highly citedYes9.18E+062.00E+07Academia
97
VisionUniversity of OxfordAcademia
R Fergus, P Perona, A Zisserman
18/06/20032003
Object Class Recognition by Unsupervised Scale-Invariant Learning
https://ieeexplore.ieee.org/document/1211479
2.97E+03Highly citedYes4.51E+023.50E+03Academia
98
CNN Best PracticesVision
Character recognition
One Microsoft WayIndustry
PY Simard, D Steinkraus, JC Platt
06/08/20032003
Best practices for convolutional neural networks applied to visual document analysis
https://ieeexplore.ieee.org/document/1227801
3.07E+03Highly citedYesMNIST5.00E+04Industry
99
Stanford UniversityAcademia
B. Taskar, C. Guestrin, and D. Koller
01/03/20042004
Max-margin markov networks
https://papers.nips.cc/paper/2003/file/878d5691c824ee2aaf770f7d36c151d6-Paper.pdf
1.76E+03Highly citedYes6.00E+02Academia
100
Soongsil UniversityAcademia
KS Oh, K Jung
01/06/20042004
GPU implementation of neural networks
https://www.sciencedirect.com/science/article/pii/S0031320304000524
4.71E+02YesAcademia