*Function* draws from a dropout neural network. This new visualisation technique depicts the distribution over *functions* rather than the predictive distribution (see demo [below](http://mlg.eng.cam.ac.uk/yarin/blog_2248.html#demo)).
This is Yarin Gal's PhD Thesis. It is awesome for people who want to learn Bayesian Deep Learning.
The thesis can be obtained as a Single PDF (9.1M), or as individual chapters (since the single file is fairly large):
- Contents 目录(PDF, 36K)
- Chapter 1: The Importance of Knowing What We Don't Know 知所不知的重要性(PDF, 393K)
- Chapter 2: The Language of Uncertainty 不确定性的语言 (PDF, 136K)
- Chapter 3: Bayesian Deep Learning 贝叶斯深度学习 (PDF, 302K)
- Chapter 4: Uncertainty Quality 不确定性的质量 (PDF, 2.9M)
- Chapter 5: Applications 应用 (PDF, 648K)
- Chapter 6: Deep Insights 深层洞察力 (PDF, 939K)
- Chapter 7: Future Research 未来研究(PDF, 28K)
- Bibliography (PDF, 72K)
- Appendix A: KL condition KL 条件 (PDF, 71K)
- Appendix B: Figures (PDF, 2M)
- Appendix C: Spike and slab prior KL (PDF, 28K)
