Preview

01 - Artificial Intelligence

 1. The image below shows Silver didrachma from Crete depicting Talos, an ancient mythical automaton with artificial intelligence!
Didrachm_Phaistos_obverse_CdM.jpg

  FALSE

  TRUE

 2. Artificial Intelligence is a field of computer science wherein the cognitive functions of the human brain are studied and tried to be ______________.

  replicated using non-physical particles and quantum computers.

  replicated on a machine/system.

  replicated using molecules instead of bits in a computer.

  replicated in a dead human's brain.

 3. Facebook uses ___________________. It works on the face verification algorithm, structured by Artificial Intelligence (AI) techniques using neural network models.
Facebook_AI_Face_Recognition.jpg

  DeepFace for face verification.

  FaceSurge for facial reconstruction.

  DeepBlue for face recognition.

  FaceBlue for facial surgery.

 4. The following table shows the differences between weak and strong AI. What are examples (applications/features) of weak AI?
weak_strong_AI_cert.png

  Quantum Computers, Physical re-creations

  Robotics, Surgical AI

   Skynet or HAL9000

  Siri, Alexa

 5. Which of the following are valid programming languages used in AI?

  R

  All of the listed items are valid

  Python

  Java

 6. Generally, a Reinforcement Learning (RL) system is comprised of two main components. What are they? (2 marks)
rl_interaction.png

 7. Read the following excerpt and fill in the blanks
Let us suppose that our agent is learning to play counterstrike. 
The RL process can be broken down into the below steps:

The RL Agent (Player1) collects state S? from the environment 
(Counterstrike game)

Based on the state "S", the RL agent takes an action "A", 
(Action can be anything that causes a result i.e. if the agent
 moves left or right in the game). Initially, the action is random
The environment is now in a new state "S" (new stage in the game)

The RL agent now gets a reward "R" from the environment. 
This reward can be additional points or coins
This RL loop goes on until the RL agent is dead or reaches 
the destination, 

and it continuously outputs a sequence of ___________________________.
counterstrike_AI_cert.jpg

  action and reward

  state, action, and reward.

  state, counter and reward

  state, new state and action

 8. The mathematical approach for mapping a solution in Reinforcement Learning is called _______________ (MDP).
MDP_AI_cert.png

  Martinova's Deviation Purge

  Markov's Density Program

  Markov?s Decision Process

  Mental Destination Programming

 9. Generally speaking, when referring to searching algorithms, the ?depth first search? method takes less memory.

  TRUE

  FALSE

 10. The ____________is the best way to go for game playing problem, as it will use the technique based on intelligent guesswork. For example, Chess between humans and computers as it will use brute force computation, looking at hundreds of thousands of positi

  Hashed approach

  Breadth-first approach

   Heuristic approach

  Binary tree approach

 11. A hybrid Bayesian network contains _____________________.

  3d arrays

  graphs with tree like structures

  binary trees which are restricted to four levels

  both discrete and continuous variables.

 12. Tower of Hanoi is a mathematical puzzle that shows how recursion might be utilized as a device in building up an algorithm to take care of a specific problem. Using a decision tree and a _______________________ in AI, we can solve the Tower of Hanoi.

  P vs NP method

  Heuristic approach

  breadth-first search (BFS) algorithm

  depth-first search (DFS) algorithm

 13. The Turing test is a method to test ____________________________. A machine is used to challenge human intelligence, and when it passes the test it is considered intelligent.

  a machine's ability to perform complex computations in polynomial time

  a machine?s ability to match the human-level intelligence

  a human's ability to communicate effectively with a machine

  a machine's ability to follow programmed instructions

 14. Fuzzy logic is a subset of AI; it is a way of encoding human learning for artificial processing. It is a form of many-valued logic. It is represented as _____________ and one application is ________________.

  ITERATION rules / facial pattern recognition

  KNOWLEDGE based system logic / control of consciousness

   IF-THEN rules /stock trading

  IF-THEN rules / the creation of DNA from scratch

 15. What is a partial-order planning? A problem has to be solved in a ______________ to attain the goal. The partial-order plan specifies all actions that need to be undertaken but specifies an order of the actions only when required.

  non-linear approach

  seemingly illogical

  sequential approach

  counter-intuitive

 16. Artificial Superhuman Intelligence (ASI): An example is the Alpha 2 which is the first _____________.

  molecular AI machine

  humanoid ASI robot.

  finite state machine that mimics brain activity

  martinova's Deviation Purge

 17. A Bayesian network could be used to study the relationship between ______________. Given various symptoms, the Bayesian network is ideal for computing probabilities.

  mathematical and non mathematical probabilities.

   diseases and symptoms.

  functions and procedures.

  humans and machines.

 18. The crop yield in India is degrading because farmers are unable to detect diseases in crops during the early stages. Can AI be used for disease detection in crops?
leaf_AI_image_processing.png

  Nearly, AI to implement image processing and classification for diseases is being developed.

  No, AI would not be appropriate for use in this case.

  No, the AI to implement image processing has not yet been developed and is a long way off.

  Yes, AI can be used to implement image processing and classification techniques for extraction and classification of leaf diseases.

 19. What data structure, often used in AI, is associated with the Depth first search algorithm?

  A non-linear binary tree

  A stack

  A queue

  A 3d matrix

 20. The halting problem asks, given a computer program and an input, ___________________________________.
x = input()
while x:
    pass

  will the program run forever if it is given an infinite amount of data?

  will the program ever be able to predict its own termination and alter its input if this is suspected?

  will the program ever be able to select its own input and therefore create its own way (acquire free will)

  will the program terminate or will it run forever?