Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
14 Cards in this Set
- Front
- Back
- 3rd side (hint)
Supervised learning goal |
to learn a mapping from input x to output y given set of input-output labeled dataset |
labeled |
|
Unsupervised Learning goal |
Find interesting pattern in an unlabeled dataset |
|
|
Classification |
Learn mapping of input x into ouputs class y. |
|
|
Binary classification |
Classification with number of output class equal to 2 |
|
|
Multiclass classification |
Classification where number of output class is more than 2 |
|
|
Multilabel classification |
Classification where an input can be classified into several output class |
|
|
Regression |
Mapping of input x into y where the response variable is continous |
|
|
Example of unsupervised learning |
1. Discovering cluster 2. Discovering latent factor 3. Discovering graph structure |
|
|
PCA |
Principal Component Analysis. os an unsupervised learning which does dimensionality reduction. |
|
|
Parametric model |
ML model which has fixed number of parameter |
|
|
Non parametric model |
ML model which has growing number of parameter as the training set grows |
|
|
Overfitting |
Model behavior which perform good in training set but doesn't capture generalized behavior of the training set which then perform bad during testing |
|
|
Underfit |
Model behavior that produce high error against the real result |
|
|
No free lunch theorem |
all models are wrong but some are useful |
|