Commit d2eb9a9f authored by Ying-Qiu Zheng's avatar Ying-Qiu Zheng
Browse files

Update 2021JUL21.md

parent 30f7fa14
......@@ -95,13 +95,13 @@ end
XLtrain[:, rand(1:n_samples, Int(round(n_samples / 10)))] .= randn(d, Int(round(n_samples / 10))) .* 2
```
#### Results
Note that "High+Low" and "Low" are initialised from the same points.
Note that "High+Low" and "Low" are initialised from the same points. "column noise", "column zero", and "outlier" correspond to the three scenarios, i.e., (1) where the low-quality data are noiser (while all features remain informative); (2) where the low quality data are not only noiser but also less informative (some features are zero-ed); (3) where the low quality data are noiser and have more outlier samples.
- d = 3
- d = 3 (three features)
![res1](/figs/2021JUL21/d3.svg)
- d = 10
- d = 10 (ten features)
![res2](/figs/2021JUL21/d10.svg)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment