most supervised learning will revolve around a key few algorithms.
logistic regression for classification
linear regression for regression.
Supervised
- input data is labeled
- data is classified based on training dataset
- used for prediction
- known number of classes
Ex: feed apples, fishes, pears to the algo, in labeled columns and tell the algo which one is which...then feed input to classify
Unsupervised
- input data is unlabeled
- assigns properties of given data to classify it
- used for analytics
- unknown number of classes
Ex: feed apples, fishes, pears to the algo, and algo will cluster 3 groups
No comments:
Post a Comment