Data, Models and Training - Quiz

Question 1

Why is data important in machine learning?

Data provides examples from which the model can learn patterns Data automatically writes the application code Data replaces the machine learning model Data guarantees that every prediction will be correct

Question 2

What happens to a model during training?

Its parameters are adjusted so that it becomes better at the task Its parameters are permanently deleted It stops processing data It automatically becomes conscious

Question 3

Why does the quality of training data matter?

Poor data can cause the model to learn poor or misleading patterns Data quality has no effect on AI systems Poor data always makes a model faster Data quality only matters after deployment

Question 4

What is overfitting?

A model performs poorly on training data but well on new data A model becomes too closely adapted to its training data and performs poorly on new data A model has no training data A model is unable to produce any output

Question 5

What does generalization mean in machine learning?

The model can perform well on new data that it did not encounter during training The model memorizes every training example exactly The model never needs testing The model only works with the original training examples