Introduction Flashcards

questions about the first lecture of "Introduction to AI" given by Johannes Fürnkranz at JKU (2024W)

1
Q

What is the classic definition of AI? (John McCarthy)

A

„the science and engineering of
making intelligent machines,
especially intelligent computer
programs.
It is related to the similar task of
using computers to understand
human intelligence, but AI does not
have to confine itself to methods
that are biologically observable.“

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Who was Alan Turing?

A

British mathematician at the
University of Manchester. Turing is often credited as
being the key founder of theoretical computer science
and AI.
Namegiver to the Turing Award.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is Machine Learning? (Tom Mitchell)

A

the science “concerned with the
question of how to construct
computer programs that
automatically improve with
experience”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is Deep Learning? (Geoffrey Hinton, Yann LeCun, Yoshua Bengio)

A

a form of
machine learning
that makes use of
artificial neural
networks

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

How are Deep Learning, Machine Learning and AI connected to one another?

A

Deep Learning is a part of Machine Learning, which in turn is part of AI.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What are the two dimensions when defining AI?
Which combination do most people see as true?

A
  • Thought process or reasoning vs behavior or action
  • Success according to human standards vs success according to rationality
  • Most people see “System that acts rationally” as the truest definition.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Who said the following: “The exciting new effort to make computers think… machines with minds, in the full and literal sense.”
Within the two-dimensional matrix of definitions for AI, in which quadrant does this quote fall?

A

Haugeland
Matrix: System that thinks like humans

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Who said the following: “[The automatation of] activities that we associate with human thinking, activities such as decision-making, problem solving, learning,…”
Within the two-dimensional matrix of definitions for AI, in which quadrant does this quote fall?

A

Bellman
Matrix: System that thinks like humans

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Who said the following: “The art of creating machines that perform functions that require intelligence when performed by people.”
Within the two-dimensional matrix of definitions for AI, in which quadrant does this quote fall?

A

Kurzweil
Matrix: System that acts like humans

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Who said the following: “The study of how to make computers do things at which, at the moment, people are better.”
Within the two-dimensional matrix of definitions for AI, in which quadrant does this quote fall?

A

Rich and Knight
Matrix: System that acts like humans

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Who said the following: “The study of mental faculties through the use of computational models.”
Within the two-dimensional matrix of definitions for AI, in which quadrant does this quote fall?

A

Charniak and McDermott
Matrix: System that thinks rationally

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Who said the following: “The study of the computations that make it possible to perceive, reason, and act.”
Within the two-dimensional matrix of definitions for AI, in which quadrant does this quote fall?

A

Winston
Matrix: System that thinks rationally

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Who said the following: “Computational Intelligence is the study of the design of intelligent agents.”
Within the two-dimensional matrix of definitions for AI, in which quadrant does this quote fall?

A

Poole et al.
Matrix: System that acts rationally

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Who said the following: “AI… is concered with intelligent behavior in artifacts.”
Within the two-dimensional matrix of definitions for AI, in which quadrant does this quote fall?

A

Nilsson
Matrix: System that acts rationally

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is Cognitive Science in AI?

A

It brings together computational models from AI and experimental techniques from psychology to construct precise and testable theories of the mind.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How did Aristotle capture the laws of thought?

A

Correctness depends on irrefutability of reasoning processes -> the first pattern of correct formal reasoning: “Socrates is a man, all men are mortal, therefore Socrates is mortal.”

17
Q

What are the problems with logic programming and with systems that think rationally?

A
  • it is hard to formalize knowledge exactly (ie Feigenbaum Bottleneck)
  • can be tricky to implement different rules of logic that don’t contradict each other
  • human decision making is not just logic but also intuition
18
Q

How can it be tested if a system acts like humans?

A

The Imitation Game/Turing Test

19
Q

How does the Imitation Game/Turing Test work?

A

A human is connected to a computer and another human and through messaging has to find out which of the opponents is human and which one is the computer.

20
Q

What are the problems with the Turing Test?

A
  • not reproducible
  • not constructive
  • not amenable to mathematical analysis
21
Q

What are problems of “System that acts rationally” over the other three combinations of the two-dimensional matrix of AI definition?

A
  • perfect rationality is only feasible in ideal environments
  • rationality is often not a very good model of reality
22
Q

What is an algorithm?

A

Unambiguous specifications (step-by-step procedure) of how to solve a class of problems in finite time:
* the sequence of steps taken for the same problem is always the same.
* you should get a result after some time
* you should always get the right result

23
Q

What are areas where AI is currently used?

A
  • health care (supports people in need)
  • household (roomba)
  • motor vehicles (self driving cars, parking assistant,..)
  • art
  • games (chess, GO)
24
Q

What are some subfields of AI (research)?

A
  • Problem Solving and Search
  • Game Playing
  • Knowledge Representation
  • Planning
  • Machine Learning
  • Neural Networks
  • Natural Language Understanding
  • Computer Vision
  • Robotics
25
Q

What are the current trends/focus’ in AI?

A
  • exploit the strengths of the computer (fast repetitious computations, statistics)
  • focus on particular tasks and not on solving AI as a whole
  • strong scientific standards