1.Lazy:
a.Defers data processing until it recieves a request to classify an unlabeled example.
b.Replies to a request for information by combining its stored training data.
c.Discards the constructed answer and any intermediate results.
2.Eager:
a.Compiles its data into a compressed description or model.
b.Discards the training data after complication of the model.
c.Classifies incoming patterns using the induced models,which is retained for future inquests.
3.Trade off:
a.Lazy algorithms have fewer cumputational costs than eager algorithm during training.
b.Lazy algorithms have greater storage requirments and higher computation costs on recall.