Week 2 – Things that think

Question 1

this is a rule that has been executed or used

Answer 1

describe a

fired rule

Question 2

name the subsytems required for a

think-sense-act model robot

Answer 2

a robot of this model requires:

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

Question 3

give two observations of

Valentino Braitenberg light seeking machine

Answer 3

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

Question 4

who is

John Searle

Answer 4

an american philosipher who created concepts such as

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

Question 5

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

Answer 5

describe the structure of a

rule

Question 6

describe the

sense-act model

Answer 6

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

Question 7

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

Answer 7

name 3 methods that a robot can take to

resolve conflict in rules

Question 8

describe

Learnt reactive behaviour

Answer 8

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

Question 9

describe the

input layer of an artificial neural network

Answer 9

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

Question 10

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

Answer 10

who are

elmer and elsie

Question 11

this problem solving method can be described as:

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

Answer 11

in the context of problem solving desribe

conforming to habit

Question 12

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

Answer 12

name the 5 major

parts that make up a robots architecture

Question 13

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

Answer 13

describe

strong A.I

Question 14

describe the structure of a

rule

Answer 14

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

Question 15

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

Answer 15

describe the

hidden layer of an artificial neural network

Question 16

the layers for this include:

• input layer
• hidden layer
• output layer

Answer 16

what are the 3

layers of an artificial neural network

Question 17

in the context of problem solving desribe

conforming to habit

Answer 17

this problem solving method can be described as:

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

Question 18

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

Answer 18

describe

machine learning

Question 19

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

Answer 19

describe the

Information processing system of a robot

Question 20

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

Answer 20

how did

grey walters robots elmer and elsie actually work

Question 21

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

Answer 21

in the context of problem solving desribe

logical deduction

Question 22

in the context of neural nets describe

generalisation

Answer 22

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

Question 23

read the relationship between

alan turings turning test / imitation game

and

john searles chinese room

Answer 23

Turing test | Definition & Facts | Britannica

Question 24

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

Answer 24

describe

weak A.I

Question 25

describe the ## Footnote **Information processing system of a robot**

Answer 25

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

Question 26

[Turing test | Definition & Facts | Britannica](https://www.britannica.com/technology/Turing-test)

Answer 26

read the relationship between ## Footnote **alan turings turning test / imitation game** **and** **john searles chinese room**

Question 27

this american philosipher proposed: * **strong ai** * **weak ai**

Answer 27

what are the ## Footnote **two types of A.I that were suggested by john searle**

Question 28

describe ## Footnote **Valentino Braitenberg light avoider vehicle**

Answer 28

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

Question 29

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

Answer 29

describe a ## Footnote **triggered rule**

Question 30

in the context of facts describe a ## Footnote **phrase**

Answer 30

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

Question 31

in the context of problem solving desribe ## Footnote **logical deduction**

Answer 31

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

Question 32

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

Answer 32

name 3 ## Footnote **approaches to training a robot**

Question 33

**describe the** **hidden layer of an artificial neural network**

Answer 33

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

Question 34

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

Answer 34

how were ## Footnote **grey walters robots elmer and elsie wired**

Question 35

how did ## Footnote **grey walters robots elmer and elsie actually work**

Answer 35

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

Question 36

in the context of facts describe a ## Footnote **fact**

Answer 36

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

Question 37

what are the ## Footnote **two types of A.I that were suggested by john searle**

Answer 37

this american philosipher proposed: * **strong ai** * **weak ai**

Question 38

describe ## Footnote **deep learning**

Answer 38

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

Question 39

who is ## Footnote **Valentino Braitenberg**

Answer 39

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

Question 40

name the 5 major ## Footnote **parts that make up a robots architecture**

Answer 40

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

Question 41

in the context of problem solving desribe ## Footnote **associations**

Answer 41

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

Question 42

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

Answer 42

what are the 2 ## Footnote **parts of a fact**

Question 43

an american philosipher who created concepts such as * the chinese room * strong A.I vs Weak A.I

Answer 43

who is ## Footnote **John Searle**

Question 44

how are ## Footnote **neural networks trained**

Answer 44

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

Question 45

describe the term ## Footnote **reasoning**

Answer 45

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

Question 46

describe the ## Footnote **output layer of an artificial neural network**

Answer 46

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

Question 47

describe ## Footnote **weak A.I**

Answer 47

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

Question 48

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

Answer 48

describe the ## Footnote **sense-think-act model**

Question 49

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

Answer 49

who was ## Footnote **grey walter**

Question 50

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

Answer 50

who is ## Footnote **Valentino Braitenberg**

Question 51

a robot of this model requires: 1. perception subsytem 2. cognition subsystem 3. actuation subsystem

Answer 51

name the subsytems required for a ## Footnote **think-sense-act model robot**

Question 52

what are the 3 **layers of an artificial neural network**

Answer 52

the layers for this include: * input layer * hidden layer * output layer

Question 53

who are ## Footnote **elmer and elsie**

Answer 53

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

Question 54

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

Answer 54

in the context of facts describe a ## Footnote **fact**

Question 55

describe a ## Footnote **fired rule**

Answer 55

this is a rule that has been executed or used

Question 56

this is the ability to acquire knowledge and understanding

Answer 56

describe the term ## Footnote **cognition**

Question 57

describe the ## Footnote **cognition subsystem of a robot**

Answer 57

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)

Question 58

describe ## Footnote **strong A.I**

Answer 58

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

Question 59

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

Answer 59

describe ## Footnote **Valentino Braitenberg light avoider vehicle**

Question 60

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

Answer 60

describe the ## Footnote **sense-act model**

Question 61

these include: * **logical deduction** * **associations** * **conforming to habit**

Answer 61

name 3 ## Footnote **problem solving methods**

Question 62

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

Answer 62

how are ## Footnote **neural networks trained**

Question 63

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

Answer 63

describe ## Footnote **Learnt reactive behaviour**

Question 64

who was ## Footnote **grey walter**

Answer 64

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

Question 65

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

Answer 65

in the context of problem solving desribe ## Footnote **associations**

Question 66

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

Answer 66

in the context of facts describe a ## Footnote **phrase**

Question 67

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

Answer 67

describe ## Footnote **deep learning**

Question 68

what are the 2 ## Footnote **parts of a fact**

Answer 68

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

Question 69

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

Answer 69

in the context of neural nets describe ## Footnote **generalisation**

Question 70

name 3 methods that a robot can take to ## Footnote **resolve conflict in rules**

Answer 70

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

Question 71

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

Answer 71

describe the term ## Footnote **reasoning**

Question 72

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

Answer 72

give two observations of ## Footnote **Valentino Braitenberg light seeking machine**

Question 73

name 3 ## Footnote **approaches to training a robot**

Answer 73

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

Question 74

name 3 ## Footnote **problem solving methods**

Answer 74

these include: * **logical deduction** * **associations** * **conforming to habit**

Question 75

describe the term ## Footnote **cognition**

Answer 75

this is the ability to acquire knowledge and understanding

Question 76

describe the ## Footnote **sense-think-act model**

Answer 76

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

Question 77

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

Answer 77

describe the ## Footnote **output layer of an artificial neural network**

Question 78

how were ## Footnote **grey walters robots elmer and elsie wired**

Answer 78

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

Question 79

describe a ## Footnote **triggered rule**

Answer 79

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

Question 80

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

Answer 80

describe a ## Footnote **single artificial neuron**

Question 81

describe a ## Footnote **single artificial neuron**

Answer 81

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

Question 82

describe ## Footnote **machine learning**

Answer 82

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

Question 83

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

Answer 83

describe the ## Footnote **input layer of an artificial neural network**

Question 84

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)

Answer 84

describe the ## Footnote **cognition subsystem of a robot**