06 Checkpoint: Classic machine learning

Content and key concepts

Progress is available with JavaScript. View is not equal to development.
Eight reviews of the mechanism
Threshold: 7 out of 8. without a timer. Balls are given for answers, not for visits. This is a local self-check; the decisions will be shown after dispatch.
1. What does a low-squares fat do?
Selects parameters on how to train
Brings the test labels by hand
Changes the number of examples
2. The change of threshold at the same level changes...
Probability itself
Rule to turn probability into class
Training dataset
3. The polynomial should be selected by ...
Test after every attempt
Validation
Future user labels
4. Precion in the absence of prositative preferences ...
Always 100%.
Not determined without additional convention
Mandatoryly equals recall
5. MSE errors[0, -1 - 2]?
Your numerical response
6. Slope fat for x=[-1.0],y=[-1.1.3]?
Your numerical response
7. Precion underTP2,FP1?
Your numerical response
8. Inertia dots[0.0], [2.0] relative to [1.0]?
Your numerical response
The result will appear after all the answers have been sent.
Research and explain
Record the train and change the polynomial degree. Write down the TRAIN/validation error and explain the discrepancy. For K-means, compare the same and dispersed initial centres, mark the policy of an empty cluster.
First, shape the hypothesis, then change one parameter. Compare the numbers to the formula; state the extreme case and the limit of applicability. The free conclusion is not evaluated by a dummy automatic score.