2015机器学习十大问题

Machine Learning is a very vast field, and much of it is still an active research area. There are many interesting problems that can easily be nominated as a "top" problem, however I don't think any of them will be solved (completely)by the end of 2015.

As an example, here is a fun paper by Dr Pedro Domingos  written in 2007 about Ten Problems for the Next Ten Years. Its almost 2015, and we are notable solve any one of them completely yet, so I think these problems willremain "top problems" at least for a year!

But my 2 cent are on these topics (in no particular order) -

1. Structured prediction
   
2. Inductive transfer
   
3. Marginal MAP problem
   
4. Learning architecture of Deep Net
5. Combining Deep Learning with Statistical Relational Learning
6. Combining SVM with Probabilistic Graphical Models
7. Determining learning rate (No More Pesky Learning Rates)
8. Learning in presence of partial data (Expectation–maximization)
9. Learning Probabilistic programs
10. Banishing "black arts" from machine learning (A Few Useful Things to Know about Machine Learning)