Introduced GPT-3, demonstrating that large language models can perform new tasks from just a few examples without explicit training.
@article{brown2020language,title={Language Models are Few-Shot Learners},author={Brown, Tom B. and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},journal={arXiv preprint arXiv:2005.14165},year={2020},}
2018
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and 1 more author
Introduced BERT, which achieved state-of-the-art results on multiple NLP tasks through bidirectional context and transfer learning.
@article{devlin2018bert,title={BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},journal={arXiv preprint arXiv:1810.04805},year={2018},}
2017
Attention Is All You Need
Ashish Vaswani, Noam Shazeer, Niki Parmar, and 5 more authors
In Advances in Neural Information Processing Systems, 2017
Introduced the Transformer architecture, which revolutionized natural language processing and became the foundation for models like BERT and GPT.
@inproceedings{vaswani2017attention,title={Attention Is All You Need},author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, Łukasz and Polosukhin, Illia},booktitle={Advances in Neural Information Processing Systems},volume={30},pages={5998--6008},year={2017},}
2016
Mastering the Game of Go with Deep Neural Networks and Tree Search
David Silver, Aja Huang, Chris J. Maddison, and 8 more authors
Described AlphaGo, the first computer program to defeat a world champion at the game of Go.
@article{silver2016mastering,title={Mastering the Game of Go with Deep Neural Networks and Tree Search},author={Silver, David and Huang, Aja and Maddison, Chris J. and Guez, Arthur and Sifre, Laurent and Van Den Driessche, George and Schrittwieser, Julian and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc and others},journal={Nature},volume={529},number={7587},pages={484--489},year={2016},publisher={Nature Publishing Group},doi={10.1038/nature16961},}
2015
Human-level Control Through Deep Reinforcement Learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, and 8 more authors
Introduced Deep Q-Networks (DQN), which combined deep learning with reinforcement learning to achieve human-level performance on Atari games.
@article{mnih2015human,title={Human-level Control Through Deep Reinforcement Learning},author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A. and Veness, Joel and Bellemare, Marc G. and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K. and Ostrovski, Georg and others},journal={Nature},volume={518},number={7540},pages={529--533},year={2015},publisher={Nature Publishing Group},doi={10.1038/nature14236},}
2012
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton
In Advances in Neural Information Processing Systems, 2012
This paper introduced AlexNet, which dramatically improved image classification performance and launched the deep learning revolution.
@inproceedings{krizhevsky2012imagenet,title={ImageNet Classification with Deep Convolutional Neural Networks},author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E.},booktitle={Advances in Neural Information Processing Systems},volume={25},pages={1097--1105},year={2012},}
2009
The Quest for Artificial Intelligence: A History of Ideas and Achievements
Comprehensive history of artificial intelligence by one of the pioneers in the field.
@inproceedings{nilsson2009quest,title={The Quest for Artificial Intelligence: A History of Ideas and Achievements},author={Nilsson, Nils J.},booktitle={},year={2009},publisher={Cambridge University Press},}
1998
Gradient-Based Learning Applied to Document Recognition
Yann LeCun, Léon Bottou, Yoshua Bengio, and 1 more author
Introduced LeNet-5, a pioneering convolutional neural network architecture for handwritten digit recognition.
@article{lecun1998gradient,title={Gradient-Based Learning Applied to Document Recognition},author={LeCun, Yann and Bottou, Léon and Bengio, Yoshua and Haffner, Patrick},journal={Proceedings of the IEEE},volume={86},number={11},pages={2278--2324},year={1998},publisher={IEEE},doi={10.1109/5.726791},}
Popularized the backpropagation algorithm for training neural networks, leading to a resurgence in neural network research.
@article{rumelhart1986learning,title={Learning Representations by Back-propagating Errors},author={Rumelhart, David E. and Hinton, Geoffrey E. and Williams, Ronald J.},journal={Nature},volume={323},pages={533--536},year={1986},doi={10.1038/323533a0},}
1982
Neural Networks and Physical Systems with Emergent Collective Computational Abilities
John J. Hopfield
Proceedings of the National Academy of Sciences, 1982
Introduced Hopfield networks, which showed how associative memory could be implemented in neural networks.
@article{hopfield1982neural,title={Neural Networks and Physical Systems with Emergent Collective Computational Abilities},author={Hopfield, John J.},journal={Proceedings of the National Academy of Sciences},volume={79},number={8},pages={2554--2558},year={1982},publisher={National Academy of Sciences},doi={10.1073/pnas.79.8.2554}}
1969
Perceptrons: An Introduction to Computational Geometry
This influential work highlighted limitations of single-layer perceptrons, contributing to the first "AI winter" by demonstrating what simple neural networks could not compute.
@article{minsky1969perceptrons,title={Perceptrons: An Introduction to Computational Geometry},author={Minsky, Marvin and Papert, Seymour},journal={},year={1969},publisher={MIT Press}}
1959
Some Studies in Machine Learning Using the Game of Checkers
Described one of the first self-learning programs and introduced the term "machine learning" to the field.
@article{samuel1959some,title={Some Studies in Machine Learning Using the Game of Checkers},author={Samuel, Arthur L.},journal={IBM Journal of Research and Development},volume={3},number={3},pages={210--229},year={1959},publisher={IBM},doi={10.1147/rd.33.0210},}
1958
The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain
Introduced the perceptron, one of the first computational models of a neuron capable of learning, laying groundwork for neural networks.
@article{rosenblatt1958perceptron,title={The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain},author={Rosenblatt, Frank},journal={Psychological Review},volume={65},number={6},pages={386--408},year={1958},publisher={American Psychological Association},doi={10.1037/h0042519},}
1956
A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence
John McCarthy, Marvin L. Minsky, Nathan Rochester, and 1 more author
This proposal for the Dartmouth Conference coined the term "Artificial Intelligence" and is considered the founding document of AI as a field.
@inproceedings{mccarthy1956dartmouth,title={A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence},author={McCarthy, John and Minsky, Marvin L. and Rochester, Nathan and Shannon, Claude E.},booktitle={},year={1956},}
This seminal paper introduced what is now known as the "Turing Test" for machine intelligence, proposing that a machine could be considered intelligent if its responses were indistinguishable from a human’s.
@article{turing1950computing,title={Computing Machinery and Intelligence},author={Turing, Alan M.},journal={Mind},volume={59},number={236},pages={433--460},year={1950},publisher={Oxford University Press},doi={10.1093/mind/LIX.236.433},}
1943
A Logical Calculus of the Ideas Immanent in Nervous Activity
This pioneering work proposed the first mathematical model of a neural network, showing how simple computational units could perform complex logical operations.
@article{mcculloch1943logical,title={A Logical Calculus of the Ideas Immanent in Nervous Activity},author={McCulloch, Warren S. and Pitts, Walter},journal={The Bulletin of Mathematical Biophysics},volume={5},number={4},pages={115--133},year={1943},publisher={Springer},doi={10.1007/BF02478259},}