July 2018
Beginner to intermediate
406 pages
9h 55m
English
Admittedly, the example in the previous section was created to show the beauty of logistic regression. How does it perform on the real noisy data?
Comparing it to the best nearest-neighbor classifier (k=40) as a baseline, we see that it won't change the situation a whole lot:
|
Method |
mean(scores) |
stddev(scores) |
|
LogReg C=0.001 |
0.6369 |
0.0097 |
|
LogReg C=0.01 |
0.6390 |
0.0109 |
|
LogReg C=0.1 |
0.6382 |
0.0097 |
|
LogReg C=1.00 |
0.6380 |
0.0099 |
|
LogReg C=10.00 |
0.6380 |
0.0097 |
|
40NN |
0.6425 |
0.0104 |
We have shown the accuracy for different values of the C regularization parameter. With it, we can control the model complexity, similar to the k parameter ...
Read now
Unlock full access