Machine learning (8.2) Flashcards

1
Q

Hoe splitsing in beslisboom

A

Hoogste gini impurity bovenaan

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Wat is gini impurity

A

Onzuiverheid; 0 is puur

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Waarom geen maximale max depth

A

Overfitting

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Wat is overfitting

A

Beslisboom neemt de huidige dataset exact over, hierdoor werkt het slecht met andere dataset

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Wat is underfitting

A

Leert te weinig van de dataset, begrijpt de invloed van onafhankelijke variabele niet

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Hoe evalueren?

A

Met confusion matrix

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Wat is confusion matrix

A

Laat zien:
* True positives: correcte voorspelling
* True negatives: correcte voorspelling
* False positives: verkeerde voorspelling
* False negatives: verkeerde voorspelling

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Hoe bereken accuracy

A

???

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Hoe bereken sensitivty

A

???

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Hoe bereken specifcity

A

???

How well did you know this?
1
Not at all
2
3
4
5
Perfectly