szcf-weiya
szcf-weiya
![fig13 1](https://user-images.githubusercontent.com/13688320/35426497-842b2c6c-029e-11e8-9e12-79b4834906c0.png)
![selection_580](https://user-images.githubusercontent.com/13688320/35215646-dbd310da-ff9f-11e7-9812-c97145d9ee3f.png)
![selection_581](https://user-images.githubusercontent.com/13688320/35226192-857f62e4-ffc5-11e7-9eeb-eec061a691c5.png)
14.7节提到鸡尾酒会问题。 参考文献 1. http://blog.csdn.net/mrharvey/article/details/18598605 2. http://research.ics.aalto.fi/ica/cocktail/cocktail_en.cgi 有空去实践一下
details: [section 15.3](https://esl.hohoweiya.xyz/15%20Random%20Forests/15.3%20Details%20of%20Random%20Forests/index.html)
details: [section 5.2](https://esl.hohoweiya.xyz/05%20Basis%20Expansions%20and%20Regularization/5.2%20Piecewise%20Polynomials%20and%20Splines/index.html) Is there an example to support the claim that "terms like this are typically included with other terms in the model."?
In section 11.7, it claims that "The training set error for all of the networks was 0%, since in all cases there are more parameters than training observations." (page 406)...