Introduction to Artificial Intelligence Flashcards

Topics: History, Formal Systems, Neural Networks

You may prefer our related Brainscape-certified flashcards:
1
Q

What is a computer?

A

• John Haugeland (1985) defined a computer as an interpreted, automatic, formal system

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

What is a formal system?

A
  • A formal system is like a game in which tokens are manipulated according to rules.
  • There are three essential properties of formal systems: “token manipulation”, “digitality” and “finite playability”
  • They are also self-contained, and decomposable into totally algorithmic processes. This means that it is multiply realizable and cannot contain homunculi
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the requirements of defining a “token manipulation game?”

A

You need to specify: • What the tokens are • What their starting configuration is • What the rules are

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

What is the earliest investigation of non-brain like structures?

A
  • Came from Warren McCulloh and Walter Pitts in 1943; they viewed the neuron as a kind of ‘logic threshold’
  • McCulloch and Pitts showed how to encode a various logical propositions in networks of these units.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is connectionism?

A
  • Described as the ‘brain’ model of the mind.
  • Neurophysiology is an inspiration for connectionist models
  • Also called parallel distributed processing
  • Heart of the connectionist approach: “Intelligence emerges from the interactions of large numbers of simple processing units”
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is a digital system?

A
  • A set of positive and reliable techniques for producing and re-identifying tokens or configurations of tokens from some pre-specified set of types
  • Elegant definition: a digital system is a set of positive write/read techniques.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What did Turing mean when he used the term “unorganized machines”?

A
  • It was his conception of brain like structures for performing computations
  • These were networks of interconnected neuron like structures
  • Turing claimed that they are “about the simplest model of a nervous system”.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

When was the ‘connectionist’ bible released?

A

1986

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

What is multiple realisability?

A

• It is the most important relationship between functionalism an AI.

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

What is a reliable technique (in the context of digital systems)?

A

• A technique is reliable if it has a high probability of success

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

What is a positive technique (in the context of digital systems)?

A
  • A technique is positive if you can succeed completely by using it
  • Note: A positive technique isnt guaranteed to succeed
  • Example: Counting people in a room.
  • Non-example: Going on a date, Writing a novel
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Who is the grandfather of the dynamical approach to AI?

A

David Hume - he wanted to be the Newton of the mind and figure out the laws of consciousness

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

What is meaning holism? Why is it a challenge for strong AI?

A
  • One thing that makes meaning hard to formalize is the possibility of meaning holism
  • This is the idea that to understand one word, you need to understand others, and to understand them, you must understand others
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Describe computational functionalism.

A

• It is the view that mental states and events (i.e pain, beleifs, desires, thoughts..) are computational states of the brain.

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