# Machine Learning - Model Evaluation Flashcards Preview

## Machine Learning > Machine Learning - Model Evaluation > Flashcards

Flashcards in Machine Learning - Model Evaluation Deck (20)
1
Q

Accuracy

A

Percent of all predictions that were correct.

2
Q

Confusion Matrix

A

A matrix showing the predicted and actual classifications. A confusion matrix is of size LxL, where L is the number of different label values. Rows for each of the actual values cross-tabbed against columns of the predicted values.

3
Q

Cross-validation: Overview

A

A method for estimating the accuracy of an inducer by dividing the data into k mutually exclusive subsets, or folds, of approximately equal size. The inducer is trained and tested k times. Each time it is trained on the data set minus a fold and tested on that fold. The accuracy estimate is the average accuracy for the k folds.

4
Q

Cross-validation: How

A

Leave-one-out cross validation

K-fold cross validation

Training and validation data sets have to be drawn from the same population

The step of choosing the kernel parameters of a SVM should be cross-validated as well

5
Q

Model Comparison

A

...

6
Q

A

The method preferred by statisticians for determining which variables to include in a model. It is a modified version of R^2 which penalizes each new variable on the basis of how many have already been admitted. Due to its construct, R^2 will always increase as you add new variables, which result in models that over-fit the data and have poor predictive ability. Adjusted R^2 results in more parsimonious models that admit new variables only if the improvement in fit is larger than the penalty, which improves the ultimate goal of out-of-sample prediction. (Submitted by Santiago Perez)

7
Q

Model Evaluation: Decision tables

A

simplest way of expressing output from machine learning, cells in table represent the resulting decision based on the row and column which represent the conditions

8
Q

Model Evaluation: Mis-classification error

A

Define Test error as summed error for classification (false prediction)

9
Q

Model Evaluation: Negative class

A

Negative means not having the symptoms

10
Q

Model Evaluation: Positive class

A

presence of something we are looking for - 1

11
Q

Model Evaluation: Precision

A

Of all predicted positives, how many are positive?

12
Q

Model Evaluation: Recall

A

Of all positives how many were predicted as positive?

13
Q

Model Evaluation: True negative

A

Hypotheses correctly predicts negative output.

14
Q

Model Evaluation: True positive

A

Hypotheses correctly predicts positive output.

15
Q

Model Selection Algorithm

A

algorithm that automatically selects a good model function for a dataset.

16
Q

Precision

A

Percent of predicted Positives that were correct.

17
Q

P-values

A

...

18
Q

A

...

19
Q

Sensitivity

A

aka Recall or True positive rate. Percent of actual Positives that were correctly predicted.

20
Q

Specificity

A

aka True negative rate. Percent of actual Negatives that were correctly predicted.