Turing T2 2023-2024

Which of the following is (are) objectives of artificial intelligence (AI)?

• To create autonomous machines/systems that can replace human experts

• To model and process intelligence so as to build intelligent entities (systems)

• Scientific motivations for creation of new exact algorithms and heuristics

• A super powerful system that can solve general problems like human-being

An AI agent perceives and acts upon environment using _____

• perceiver

• actuators

• sensors

• responders

Which of the following is (are) FALSE?

• Weak AI are machines that are made to act as if they were intelligent

• Strong AI are machines that act intelligently and have real conscious minds

• Every problem is a “virtual” tree of all possible (successful or unsuccessful) solutions

• The Turing test is a generative approach to determine whether or not a system is intelligent

How does an ideal rational agent know that it is doing the right thing (evaluating its success)?

• It uses performance measures to evaluate its success

• It knows that it is doing the right thing based on experience

• There is an external agent to provide feedback to the ideal rational agent

• It uses a reward/punish mechanism to evaluate its success

A _______ agent measures how efficient a state to achieve the goal.

• model-based

• utility-based

• goal-based

• simple reflex

The accurate description about machine learning is (are)_____________

• The autonomous acquisition of knowledge through the use of manual programs

• The autonomous acquisition of knowledge through the use of computer programs

• The science of developing software applications that learn from data

• The selective acquisition of knowledge through the use of computer programs

Which statement below describe(s) precisely about inductive machine learning?

• It applies some form of learning algorithm to automatically identify useful rule

• It concerns on developing software agents to take actions in an environment to maximize rewards

• It simulates the judgment and behavior of a human or an organization that has expert knowledge and experience in a particular field

• It involves the process of learning by examples, where a system, from a set of observed instances tries to induce a general rule

Reinforcement learning ________________

• uses the same error function as supervised learning

• uses input and output data

• implements the reward policy in solving a problem

• receives feedback after a sequence of steps

Entropy is ____________

• a measure of correlation between numeric variables

• used to calculate information gain

• a measure of information content

• is used to calculate overfitting

The measures used for determining the best split are usually based on the level of impurity of nodes in a decision tree.  Which of the following is(are) an impurity measure(s)?

• Gini index

• Entropy

• Classification error

• Pruning