Machine Learning - Overview - Instance Vs Model Based Learning Tutorial

1. Instance-based learning:

(sometimes called memory-based learning) is a learning algorithm in which instead of performing explicit generalization( or model training), it compares new problem instances with instances seen in training, which have been stored in memory. And provide the output based on the instances seen in the training data without actual training.

Ex- k-nearest neighbor, decision tree

2. Model-based learning:

Model-based learning is a learning algorithm in which the training data get actually trained and find the behavior (parameter) between input and output features by drawing mathematical functions.

Ex- Linear Regression, Logistic, etc.