最近打算系统的学习下deep learning。总结了下经典的入门材料:
1. 文章Survey:参见 http://deeplearning.net/reading-list/
- Representation Learning: A Review and New Perspectives, Yoshua Bengio, Aaron Courville, Pascal Vincent, Arxiv, 2012.
- The monograph or review paper Learning Deep Architectures for AI (Foundations & Trends in Machine Learning, 2009).
- Deep Machine Learning – A New Frontier in Artificial Intelligence Research – a survey paper by Itamar Arel, Derek C. Rose, and Thomas P. Karnowski.
- Graves, A. (2012). Supervised sequence labelling with recurrent neural networks(Vol. 385). Springer.
- Schmidhuber, J. (2014). Deep Learning in Neural Networks: An Overview. 75 pages, 850+ references, http://arxiv.org/abs/1404.7828
, PDF & LATEX source & complete public BIBTEX file under http://www.idsia.ch/~juergen/ deep-learning-overview.html.
2. 最近学术界的研究进展(cvpr 2014 tutorial)
https://sites.google.com/site/deeplearningcvpr2014/, 阅读了部分材料, 这里面的介绍比较系统和前沿,读起来也不太难理解,有空详细阅读下reference。
3. 视频介绍入门:
hinton 在coursera的neutral network
Hugo 的视频https://www.youtube.com/playlist?list=PL6Xpj9I5qXYEcOhn7TqghAJ6NAPrNmUBH
4. tools:
https://github.com/torch, 工业界用的多,用lua,速度快,容易嵌入c,
http://deeplearning.net/software/pylearn2/, python易编程。
比较: http://arxiv.org/pdf/1308.4214.pdf
5. 入门教程:http://ufldl.stanford.edu/wiki/index.php, 很赞, Ng的教程特别容易理解。