Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

TM129: Robotics and A.I > Week 2 – Things that think > Flashcards

Week 2 – Things that think Flashcards

1
Q

this is a rule that has been executed or used

A

describe a

fired rule

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

name the subsytems required for a

think-sense-act model robot

A

a robot of this model requires:

  1. perception subsytem
  2. cognition subsystem
  3. actuation subsystem
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

give two observations of

Valentino Braitenberg light seeking machine

A

two observations for this machine are:

  • there is no programming such as if and else it s simply hard-wired and appears to show a specific behaviour
  • The behaviour is spawned from how the sensors are connected to the actuators
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

who is

John Searle

A

an american philosipher who created concepts such as

  • the chinese room
  • strong A.I vs Weak A.I
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

the structure of this is:

  • Condition/antecedent - a fact that may or may not be true
  • Consequent - a fact that is true if the antecedent was true

example

Condition/antecedent - if my dog is eating her dinner is true

Consequent - then my dog is wagging her tail is true

A

describe the structure of a

rule

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

describe the

sense-act model

A

this model describes how an action is carried out only through sensory information

  • robots - will act depending on what its sensors are detecting
  • humans - will act/react according to what their senses tell them

important note

no processing or thinking is required it is an action carried out only through what the senses are reading

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

strategies to overcome this are:

  • A rule can be given a higher priority
  • The order in which instructions are written
  • Which rues have not recently fired
A

name 3 methods that a robot can take to

resolve conflict in rules

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

describe

Learnt reactive behaviour

A

this is behaviour that has been learnt and is now an automatic reflex

it can be said that this fits the sense-act model

example

proper use of brakes and what action to take when a dangerous situation arises whilst driving

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

describe the

input layer of an artificial neural network

A

this layer of an artificial neural network receives data, such as readings from a sensor

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

the first robots programmed by Grey walter between 1948 and 1949 that were capable of perception and actuation and so fit the sense-act model

A

who are

elmer and elsie

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

this problem solving method can be described as:

using a fact solely because it remains working for the specific problem

A

in the context of problem solving desribe

conforming to habit

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

these include:

  • Mechanical assembly - this includes everything that holds the robot together
  • Power subsystem - this includes anything that is the source of the robots power
  • Sensory subsystem - this includes any sensors that supply the robot with input
  • Mobility/actuation subsystem - includes anything that allows the robot to move or cary out any orther useful tasks
  • Control subsystem - anything that allows the robot to think receiving input from the sensory subsystem and providing input to the mobility/actuation subsystem
A

name the 5 major

parts that make up a robots architecture

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

this type of A.I would have human like intelligence and would have emotions and conciousness.

This is on the assumption that there is nothing mystical about human intelligence and that we really are simply a biological computer

A

describe

strong A.I

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

describe the structure of a

rule

A

the structure of this is:

  • Condition/antecedent - a fact that may or may not be true
  • Consequent - a fact that is true if the antecedent was true

example

Condition/antecedent - if my dog is eating her dinner is true

Consequent - then my dog is wagging her tail is true

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

this layer of an artificial neural network receives data from the input layer or other hidden layers.

Its job is to compute the data received

the more layers and artificial neurons in these can increase the neural networks performance

A

describe the

hidden layer of an artificial neural network

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

the layers for this include:

  • input layer
  • hidden layer
  • output layer
A

what are the 3

layers of an artificial neural network

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

in the context of problem solving desribe

conforming to habit

A

this problem solving method can be described as:

using a fact solely because it remains working for the specific problem

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

this can be described as:

a machine that can learn by using previous data / data structures

example

learning what music someone likes by recognising what other people like and applying that knowledge to the individual

A

describe

machine learning

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

the cognition subsystem is often referred to as this

this is a problem solver that will take into account any information it has before deciding what action should be taken and subsequently which actuators should be used.

Information will be held in memory and could be new from sensors or existing from past data

A

describe the

Information processing system of a robot

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

these robots worked so that the light sesor and front wheel would turn and upon the light sensor detcting light it would turn its wheels towards that light source.

However if the light became to bright it would become dazzled and move away from the light

for the touch sensor if a touch was detected then it would move away from the touch

A

how did

grey walters robots elmer and elsie actually work

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

this problem solving method can be described as:

where there is information available that will help in achieving the goal then the logical decision is to take/use this fact

A

in the context of problem solving desribe

logical deduction

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

in the context of neural nets describe

generalisation

A

this is a term to describes how neural nets (once trained) can give a correct output for data they have not seen before.

This is in contrast to a rule based system that would struggle with this situation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

read the relationship between

alan turings turning test / imitation game

and

john searles chinese room

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

this would appear to have human intelligence however would only ever be an illusion and would be acting from instructions instead of authentic understanding

A

describe

weak A.I

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

describe the

Information processing system of a robot

A

the cognition subsystem is often referred to as this

this is a problem solver that will take into account any information it has before deciding what action should be taken and subsequently which actuators should be used.

Information will be held in memory and could be new from sensors or existing from past data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

Turing test | Definition & Facts | Britannica

A

read the relationship between

alan turings turning test / imitation game

and

john searles chinese room

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

this american philosipher proposed:

  • strong ai
  • weak ai
A

what are the

two types of A.I that were suggested by john searle

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

describe

Valentino Braitenberg light avoider vehicle

A

this machine is a simple design that implements the sense-act model and conveys behaviour

It works by having two light sensors each connected to a wheel each. The stronger the light reading the faster its wheel will turn and so it will turn away from the light. Similarly switching the cables will create a light seeking robot

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

this is a rule that could have been executed/fired but did not because of a circumstance such as another rule taking priority

A

describe a

triggered rule

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

in the context of facts describe a

phrase

A

in the context of facts this can be described as a collection of words

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

in the context of problem solving desribe

logical deduction

A

this problem solving method can be described as:

where there is information available that will help in achieving the goal then the logical decision is to take/use this fact

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

these include:

  1. Natural selection (genetic algorithm) - where a successful behaviour is passed on to the next generation
  2. Artificial neural networks - a way of training robots and mimics the connectivity found in animal brains
  3. Reinforcement learning - teaching by giving a reward when correct this reinforces the correct behaviour
A

name 3

approaches to training a robot

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

describe the

hidden layer of an artificial neural network

A

this layer of an artificial neural network receives data from the input layer or other hidden layers.

Its job is to compute the data received

the more layers and artificial neurons in these can increase the neural networks performance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

these robots were wired so that the touch and light sensors would output to intermediate circuitry before being in-putted to the actuators.

This approach showed that the behaviour of a machine can depend on how its sensors and actuators are connected

A

how were

grey walters robots elmer and elsie wired

35
Q

how did

grey walters robots elmer and elsie actually work

A

these robots worked so that the light sesor and front wheel would turn and upon the light sensor detcting light it would turn its wheels towards that light source.

However if the light became to bright it would become dazzled and move away from the light

for the touch sensor if a touch was detected then it would move away from the touch

36
Q

in the context of facts describe a

fact

A

in the context of facts this can be described as a phrase that can be recognised and can have a truth value given to it

37
Q

what are the

two types of A.I that were suggested by john searle

A

this american philosipher proposed:

  • strong ai
  • weak ai
38
Q

describe

deep learning

A

this is a subset of machine learning but instead of using previous data structures it makes use of neural networks in its learning

example

finding what music someone likes instead of using past data we can let the user select like / hate this in turn allows the A.I to learn what the user likes

39
Q

who is

Valentino Braitenberg

A

an Italian researcher who in the 1980s was unaware of the sense-act model work that Grey Walter had produced 30 years prior but did investigate the same model.

he never built any of his designs but they do demonstrate behaviour using the sense-act model

40
Q

name the 5 major

parts that make up a robots architecture

A

these include:

  • Mechanical assembly - this includes everything that holds the robot together
  • Power subsystem - this includes anything that is the source of the robots power
  • Sensory subsystem - this includes any sensors that supply the robot with input
  • Mobility/actuation subsystem - includes anything that allows the robot to move or cary out any orther useful tasks
  • Control subsystem - anything that allows the robot to think receiving input from the sensory subsystem and providing input to the mobility/actuation subsystem
41
Q

in the context of problem solving desribe

associations

A

this problem solving method can be described as:

using past knowledge perhaps it has learnt new facts and so will have had associated a problem with a specific result either good or bad

42
Q

the parts of this include:

  • phrase
  • truth value

example

The Queen of England is a man is false

Where:

Phrase = The Queen of England is a man

Truth value = is false

A

what are the 2

parts of a fact

43
Q

an american philosipher who created concepts such as

  • the chinese room
  • strong A.I vs Weak A.I
A

who is

John Searle

44
Q

how are

neural networks trained

A
  1. these will first take a set of known inputs and outputs this is referred to as training data
  2. Initially this will be incorrect but by adjusting its weights when it is incorrect it can eventually be trained to give the correct output for the input

note

Training these can take a long time and can require high amounts of energy and data

45
Q

describe the term

reasoning

A

this is using cognition (gained knowledge and understanding) in order to reflect on facts and come to new facts

46
Q

describe the

output layer of an artificial neural network

A

this layer of an artificial neural network is the last layer and will produce some kind of output such as moving a motor depending on the input it has received

47
Q

describe

weak A.I

A

this would appear to have human intelligence however would only ever be an illusion and would be acting from instructions instead of authentic understanding

48
Q

this model allows for more complex behaviour in which input can be assesed and various outputs performed from the ‘thinking’ processing

A

describe the

sense-think-act model

49
Q

this man was a neuroscientist who was the first to build robots that fit the sense-act model

A

who was

grey walter

50
Q

an Italian researcher who in the 1980s was unaware of the sense-act model work that Grey Walter had produced 30 years prior but did investigate the same model.

he never built any of his designs but they do demonstrate behaviour using the sense-act model

A

who is

Valentino Braitenberg

51
Q

a robot of this model requires:

  1. perception subsytem
  2. cognition subsystem
  3. actuation subsystem
A

name the subsytems required for a

think-sense-act model robot

52
Q

what are the 3

layers of an artificial neural network

A

the layers for this include:

  • input layer
  • hidden layer
  • output layer
53
Q

who are

elmer and elsie

A

the first robots programmed by Grey walter between 1948 and 1949 that were capable of perception and actuation and so fit the sense-act model

54
Q

in the context of facts this can be described as a phrase that can be recognised and can have a truth value given to it

A

in the context of facts describe a

fact

55
Q

describe a

fired rule

A

this is a rule that has been executed or used

56
Q

this is the ability to acquire knowledge and understanding

A

describe the term

cognition

57
Q

describe the

cognition subsystem of a robot

A

this is a subsystem of a robot that will implement cognition and is coined as the brains of the robot

however this is a misleading term (covered in later topic)

58
Q

describe

strong A.I

A

this type of A.I would have human like intelligence and would have emotions and conciousness.

This is on the assumption that there is nothing mystical about human intelligence and that we really are simply a biological computer

59
Q

this machine is a simple design that implements the sense-act model and conveys behaviour

It works by having two light sensors each connected to a wheel each. The stronger the light reading the faster its wheel will turn and so it will turn away from the light. Similarly switching the cables will create a light seeking robot

A

describe

Valentino Braitenberg light avoider vehicle

60
Q

this model describes how an action is carried out only through sensory information

  • robots - will act depending on what its sensors are detecting
  • humans - will act/react according to what their senses tell them

important note

no processing or thinking is required it is an action carried out only through what the senses are reading

A

describe the

sense-act model

61
Q

these include:

  • logical deduction
  • associations
  • conforming to habit
A

name 3

problem solving methods

62
Q
  1. these will first take a set of known inputs and outputs this is referred to as training data
  2. Initially this will be incorrect but by adjusting its weights when it is incorrect it can eventually be trained to give the correct output for the input

note

Training these can take a long time and can require high amounts of energy and data

A

how are

neural networks trained

63
Q

this is behaviour that has been learnt and is now an automatic reflex

it can be said that this fits the sense-act model

example

proper use of brakes and what action to take when a dangerous situation arises whilst driving

A

describe

Learnt reactive behaviour

64
Q

who was

grey walter

A

this man was a neuroscientist who was the first to build robots that fit the sense-act model

65
Q

this problem solving method can be described as:

using past knowledge perhaps it has learnt new facts and so will have had associated a problem with a specific result either good or bad

A

in the context of problem solving desribe

associations

66
Q

in the context of facts this can be described as a collection of words

A

in the context of facts describe a

phrase

67
Q

this is a subset of machine learning but instead of using previous data structures it makes use of neural networks in its learning

example

finding what music someone likes instead of using past data we can let the user select like / hate this in turn allows the A.I to learn what the user likes

A

describe

deep learning

68
Q

what are the 2

parts of a fact

A

the parts of this include:

  • phrase
  • truth value

example

The Queen of England is a man is false

Where:

Phrase = The Queen of England is a man

Truth value = is false

69
Q

this is a term to describes how neural nets (once trained) can give a correct output for data they have not seen before.

This is in contrast to a rule based system that would struggle with this situation

A

in the context of neural nets describe

generalisation

70
Q

name 3 methods that a robot can take to

resolve conflict in rules

A

strategies to overcome this are:

  • A rule can be given a higher priority
  • The order in which instructions are written
  • Which rues have not recently fired
71
Q

this is using cognition (gained knowledge and understanding) in order to reflect on facts and come to new facts

A

describe the term

reasoning

72
Q

two observations for this machine are:

  • there is no programming such as if and else it s simply hard-wired and appears to show a specific behaviour
  • The behaviour is spawned from how the sensors are connected to the actuators
A

give two observations of

Valentino Braitenberg light seeking machine

73
Q

name 3

approaches to training a robot

A

these include:

  1. Natural selection (genetic algorithm) - where a successful behaviour is passed on to the next generation
  2. Artificial neural networks - a way of training robots and mimics the connectivity found in animal brains
  3. Reinforcement learning - teaching by giving a reward when correct this reinforces the correct behaviour
74
Q

name 3

problem solving methods

A

these include:

  • logical deduction
  • associations
  • conforming to habit
75
Q

describe the term

cognition

A

this is the ability to acquire knowledge and understanding

76
Q

describe the

sense-think-act model

A

this model allows for more complex behaviour in which input can be assesed and various outputs performed from the ‘thinking’ processing

77
Q

this layer of an artificial neural network is the last layer and will produce some kind of output such as moving a motor depending on the input it has received

A

describe the

output layer of an artificial neural network

78
Q

how were

grey walters robots elmer and elsie wired

A

these robots were wired so that the touch and light sensors would output to intermediate circuitry before being in-putted to the actuators.

This approach showed that the behaviour of a machine can depend on how its sensors and actuators are connected

79
Q

describe a

triggered rule

A

this is a rule that could have been executed/fired but did not because of a circumstance such as another rule taking priority

80
Q

this will receive data such as numbers

from this it will determine whether those numbers exceed a threshold when added. if so then the artificial neuron is fired and produces an output

Each output link of the artificial neuron may also have a weight applied so each link will have different data depending on its weight.

The weight can help determine the importance of that particular link and thus determine the input value for the next neuron

A

describe a

single artificial neuron

81
Q

describe a

single artificial neuron

A

this will receive data such as numbers

from this it will determine whether those numbers exceed a threshold when added. if so then the artificial neuron is fired and produces an output

Each output link of the artificial neuron may also have a weight applied so each link will have different data depending on its weight.

The weight can help determine the importance of that particular link and thus determine the input value for the next neuron

82
Q

describe

machine learning

A

this can be described as:

a machine that can learn by using previous data / data structures

example

learning what music someone likes by recognising what other people like and applying that knowledge to the individual

83
Q

this layer of an artificial neural network receives data, such as readings from a sensor

A

describe the

input layer of an artificial neural network

84
Q

this is a subsystem of a robot that will implement cognition and is coined as the brains of the robot

however this is a misleading term (covered in later topic)

A

describe the

cognition subsystem of a robot

TM129: Robotics and A.I (5 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions