references.bib

Download
text 158 lines 5.3 KB
  1% references.bib
  2% Sample BibTeX database with various entry types
  3% This file demonstrates common reference types used in academic writing
  4
  5@book{goodfellow2016deep,
  6    title={Deep Learning},
  7    author={Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron},
  8    year={2016},
  9    publisher={MIT Press},
 10    address={Cambridge, MA},
 11    isbn={978-0262035613},
 12    url={https://www.deeplearningbook.org/}
 13}
 14
 15@book{bishop2006pattern,
 16    title={Pattern Recognition and Machine Learning},
 17    author={Bishop, Christopher M.},
 18    year={2006},
 19    publisher={Springer},
 20    series={Information Science and Statistics},
 21    address={New York, NY},
 22    isbn={978-0387310732}
 23}
 24
 25@book{lamport1994latex,
 26    title={LaTeX: A Document Preparation System},
 27    author={Lamport, Leslie},
 28    year={1994},
 29    edition={2nd},
 30    publisher={Addison-Wesley Professional},
 31    isbn={978-0201529838}
 32}
 33
 34@article{hochreiter1997long,
 35    title={Long Short-Term Memory},
 36    author={Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
 37    journal={Neural Computation},
 38    volume={9},
 39    number={8},
 40    pages={1735--1780},
 41    year={1997},
 42    publisher={MIT Press},
 43    doi={10.1162/neco.1997.9.8.1735}
 44}
 45
 46@article{hinton2006fast,
 47    title={A Fast Learning Algorithm for Deep Belief Nets},
 48    author={Hinton, Geoffrey E. and Osindero, Simon and Teh, Yee-Whye},
 49    journal={Neural Computation},
 50    volume={18},
 51    number={7},
 52    pages={1527--1554},
 53    year={2006},
 54    publisher={MIT Press},
 55    doi={10.1162/neco.2006.18.7.1527}
 56}
 57
 58@article{bengio1994learning,
 59    title={Learning Long-Term Dependencies with Gradient Descent is Difficult},
 60    author={Bengio, Yoshua and Simard, Patrice and Frasconi, Paolo},
 61    journal={IEEE Transactions on Neural Networks},
 62    volume={5},
 63    number={2},
 64    pages={157--166},
 65    year={1994},
 66    publisher={IEEE},
 67    doi={10.1109/72.279181}
 68}
 69
 70@inproceedings{krizhevsky2012imagenet,
 71    title={ImageNet Classification with Deep Convolutional Neural Networks},
 72    author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E.},
 73    booktitle={Advances in Neural Information Processing Systems},
 74    volume={25},
 75    pages={1097--1105},
 76    year={2012},
 77    editor={Pereira, F. and Burges, C.J.C. and Bottou, L. and Weinberger, K.Q.}
 78}
 79
 80@inproceedings{he2016deep,
 81    title={Deep Residual Learning for Image Recognition},
 82    author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
 83    booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
 84    pages={770--778},
 85    year={2016},
 86    organization={IEEE},
 87    doi={10.1109/CVPR.2016.90}
 88}
 89
 90@inproceedings{vaswani2017attention,
 91    title={Attention is All You Need},
 92    author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, {\L}ukasz and Polosukhin, Illia},
 93    booktitle={Advances in Neural Information Processing Systems},
 94    volume={30},
 95    pages={5998--6008},
 96    year={2017},
 97    editor={Guyon, I. and Luxburg, U. Von and Bengio, S. and Wallach, H. and Fergus, R. and Vishwanathan, S. and Garnett, R.}
 98}
 99
100@inproceedings{devlin2019bert,
101    title={BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
102    author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
103    booktitle={Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
104    volume={1},
105    pages={4171--4186},
106    year={2019},
107    organization={Association for Computational Linguistics},
108    doi={10.18653/v1/N19-1423}
109}
110
111@article{lecun2015deep,
112    title={Deep Learning},
113    author={LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey},
114    journal={Nature},
115    volume={521},
116    number={7553},
117    pages={436--444},
118    year={2015},
119    publisher={Nature Publishing Group},
120    doi={10.1038/nature14539}
121}
122
123@article{schmidhuber2015deep,
124    title={Deep Learning in Neural Networks: An Overview},
125    author={Schmidhuber, J{\"u}rgen},
126    journal={Neural Networks},
127    volume={61},
128    pages={85--117},
129    year={2015},
130    publisher={Elsevier},
131    doi={10.1016/j.neunet.2014.09.003}
132}
133
134@online{arxiv2020gpt3,
135    title={Language Models are Few-Shot Learners},
136    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},
137    year={2020},
138    eprint={2005.14165},
139    eprinttype={arXiv},
140    eprintclass={cs.CL},
141    url={https://arxiv.org/abs/2005.14165}
142}
143
144@online{tensorflow2015whitepaper,
145    title={TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems},
146    author={Abadi, Mart{\'\i}n and Agarwal, Ashish and Barham, Paul and Brevdo, Eugene and Chen, Zhifeng and Citro, Craig and Corrado, Greg S. and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and others},
147    year={2015},
148    url={https://www.tensorflow.org/},
149    note={Software available from tensorflow.org}
150}
151
152@misc{brown2020language,
153    title={Language Models are Few-Shot Learners},
154    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},
155    year={2020},
156    howpublished={arXiv preprint arXiv:2005.14165}
157}