Question

Theory of generalisation was put forward by

Answer 1

Very commonly, ‘Generalization’ is given a narrow & objective definition of quantifying how well a certain Prediction algorithm is expected to predict on that specific prediction task in future or on unseen data.

This is already very useful and yields useful:

Theories like Statistic Learning Theory, VC Dimension

Concepts like Overfitting & how many Training samples are necessary for training a model

Practices like Train-Validation-Test splits

Answer 2

Answer:

Charles judd gave theory of generalisation.