Question 1

How could machine learning make a robot autonomous?

Options :

A : Use OCR, optical character recognition, to read documents

B : Use NLP (Natural Language Processing) to listen

C : Use actuators to modify its environment

D : Learn from sensor data and plan to carry out a task.

Answer: D

Question 2

What technique can be adopted when a weak learners hypothesis accuracy is only slightly better than 50%?

Options :

A : Over-fitting

B : Activation.

C : Iteration.

D : Boosting.

Answer: D

Question 3

What is defined as a philosophy, or set of assumptions and/or techniques, which characterise an approach to a class of problems?

Options :

A : An approach.

B : A set

C : A paradigm.

D : An algorithm.

Answer: C

Question 4

Splitting data into Training and Test data sets is part of what?

Options :

A : Machine learning data preparation.

B : Batch learning.

C : Machine learning post processing.

D : High performance computing strategy.

Answer: A