Brainscape's Knowledge GenomeTM

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


See full index

COM1005 - Machines and Intelligence > Lesson ? - Revision for Assessment 1 > Flashcards

Lesson ? - Revision for Assessment 1 Flashcards

1
Q

When was the Gestation and Birth Period of AI

Lesson 3

A

1943-1956

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

When were the Golden Early Years

A

1956-1969

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

When was the First AI winter?

A

1966-73

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

When was the rise of Knowledge-based and Expert Systems?

A

1969-89

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

When was the start of the rise of New paradigms

continuing until now

A

1986

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

When was the start of the birth of the Scientific Method, Big Data and Deep Learning?

Continuing until the present day

A

1987

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

what was Pitts-McCulloch’s paper about

A

the first description of a neural network

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

Marvin Minsky was a student of who?

A

Pitts and McCulloch

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

Who built the first neural net machine?

A

Marvin Minsky and Dean Edmonds

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

name of McCulloch-Pitts 1943 paper

A

A Logical Calculus of Ideas Immanent in Nervous Activity

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

1st work in AI

A

McCulloch Pitts 1943, A Logical Calculus of Ideas Immament in Nervous Activity

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

Who is credited with creating/popularising formal propositional logic

A

Russell and Whitehead

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

neurons

A

electrically excitable cells that process and transmit info through electrical and chemical signals

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

3 parts of the artificial neuron

A

Dendrite, Soma, Axon

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

phi is a ______ function

A

step-like

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

what is fed into a neuron

A

inputs with associated weights

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

what does the neuron do with the inputs and their associated weights

A

computes the weighted sum and passes it through a NON-LINEAR TRANSFER FUNCTION

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

McCulloch and Pitts showed that

A

all logical connectives/any computable function could be computed by a neural network

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

Donald Hebb

A

proposed an updating rule for modifying connection weights in artificial neurons allowing a network to be trained

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

Hebbian Learning

A

when neurons fire together, they adapt and form stronger connections with each other through repeated use

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

name and date of first neural net computer

A

SNARC, 1951

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

Who built the SNARC

A

Marvin Minsky and Dean Edmonds

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

SNARC was used to

A

model the behaviour of a rat in a maze searching for food

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

neural nets + GPUs =

A

deep learning

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

the 40 neurons in SNARC were simulated by

A

3000 vacuum tubes

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

Logic Theorist written by

A

Herbert Simon, Allen Newell, JC Shaw

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

Logic Theorist was called the first…

A

AI Program

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

Logic Theorist was created when?

A

1955-6

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

why was Logic Theorist labelled as the 1st AI program

A

the first program deliberated engineered to mimic the problem solving skills of a human

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

Simon, Newell and Shaw proved how many of Russell/Whitehead’s theorems?

A

38

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

Name of Russell and Whitehead’s paper

A

Principia Mathematica

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

How many theorems where in Whitehead and Russell’s Principia Mathematica

A

52

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

what did Shaw/Herbert/Newell do with the final of Whitehead/Russell’s theorems

A

create a shorter version

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

axiom

A

self-evident truth

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

Logic Theorist:
Given some… (APT)

A

Axioms (A), theorems previously proved (P) and a candidate theorem to prove

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
36
Q

how many methods were applied by the Logic Theorist

A

4

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
37
Q

the methods applied by the Logic Theorist

A

substitution, detachment, chaining forward, chaining backward

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
38
Q

what is substitution (Logic Theorist)

A

change logic expression (e.g. T) into a logically equivalent one (e.g. axiom in A) by substition of varaibles/replacements of connectives

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
39
Q

detachment is also known as

A

modus ponens

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
40
Q

detachment in Logic Theorist

A

create sub-goals to prove expressions (e.g. S and S -> T in order to prove T)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
41
Q

chaining forward in Logic Theorist

A

subgoals : A -> C then A -> B and B-> C

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
42
Q

chaining backward in Logic Theorist

A

subgoals: A -> C then B-> C and A -> B

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
43
Q

3 new concepts introduced using logic theorist

A

reasoning as search, heuristics and list processing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
44
Q

reasoning as search

A

proof viewed as a search starting from a hypothesis root node

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
45
Q

explain the mechanism of proof as defined by “reasoning as search”

A

expand the proof along different branches according to deductive rules and stopping when the proposition to be proved is obtained

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
46
Q

heuristics (as introduced by Logic Theorist)

A

proof tree grows exponentially thus some branches need to be pruned using rules of thumb/heuristics to limit search space while (hopefully) not losing the path to the solution

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
47
Q

List processing

A

the list processing programming language IPL

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
48
Q

IPL

A

the list processing language implemented by the authors in Logic Theorist

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
49
Q

IPL serves as the basis for which language

A

LISP

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
50
Q

who created LISP

A

John McCarthy

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
51
Q

at non-root nodes, state = ?

A

{hypothesis + derived propositions}

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
52
Q

new states are obtained from old staets by…

A

applying deductive rules

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
53
Q

objective of Dartmouth Conference (quote)

A

every aspect of learning/any other feature of intelligence can be so precisely described that a machine can simulate it

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
54
Q

The Darmouth Conference wanted to make an attempt to find out how to make a machine do what 4 things? (LAPI)

A

use language, form abstractions/concepts, solve problems reserved for humans, improve themselves

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
55
Q

which 4 researchers proposed the Conference

A

McCarthy, Minksy, Rochester, Shannon (John, Marvin, Nathaniel, Claude)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
56
Q

the Conference was attended by who else?

A

Solomonoff, Selfridge, More, Samuel, Simon and Newell (Ray, Oliver, Trenchard, Arthur, Herbert, Allen)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
57
Q

what is considered the birth point of AI

A

the Dartmouth Conference

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
58
Q

the GEY was marked by

A

overoptimism

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
59
Q

which 3 computer scientists were particularly overoptimistic

A

Simon, Newell and Minsky

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
60
Q

who funded labs and which did they fund?

A

ARPA (Advanced Research Projects Agency) - Stanford, MIT

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
61
Q

GPS

A

General Problem Solver

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
62
Q

who created General Problem Solver and when?

A

1959 - Simon and Newell

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
63
Q

the GPS was meant to reason…

A

in a human-like way to solve any formalised symbolic problem

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
64
Q

means end analysis - aspect 1

A

given a current state and goal state, attempt to reduce differenec between the two

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
65
Q

means end analysis - aspect 2

A

operations (from current state) + their outputs -> creates subgoals to reduce distance to overall goal as much as possible

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
66
Q

when did Newell and Simon formulate the physical symbol system hypothesis

A

1976

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
67
Q

what led to Newell and Simon formulating the physical symbol system hypothesis

A

success of GPS and related programs as models of cognition

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
68
Q

physical symbol system hypothesis

A

a physical symbol system has the NECESSARY and SUFFICIENT means for general intelligent action

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
69
Q

physical symbol system

A

takes symbols, combines them into expressions, and manipulates them to produce new expressions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
70
Q

the physical symbol system implies that…

A

any intelligent system must operate by manipulating symbols

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
71
Q

True/False: the implications of the physical symbol system are disputed

A

True

72
Q

who made Geometry Theorem Prover?

A

Gelernter (1959)

73
Q

Who made Advice Taker

A

McCarthy (1958)

74
Q

which reasoned with general knowledge more broadly, Advice Taker or General Problem Solver?

A

Advice Taker

75
Q

how could Advice Taker adapt to a new domain without reprogramming?

A

by separating explicit representation of world knowledge from deductive reasoning engine

76
Q

who discovered Resolution Theorem Proving?

A

J.A Robinson 1965

77
Q

what was resolution theorem proving?

A

complete theorem proving algorithm for 1st order logic

78
Q

resolution theorem proving underlies which programming language?

A

PROLOG

79
Q

Who/when created the Checkers programs?

A

Samuel

80
Q

what did Samuel’s checkers programs demonstrate?

A

the potential of computers for non-numerical tasks/AI

81
Q

what are the core ideas of alpha-beta pruning and minimax search strategy? as introduced by the Samuel’s checkers programs

A

search space too big to search exhaustively

82
Q

what was the first machine learning program

A

Samuel’s checkers program

83
Q

why was Samuel’s checkers program considered the first machine learning program

A

it learned from itself

84
Q

what was the first computer game to reach the level of a respectable amateur?

A

checkers

85
Q

why are so many programs limited to working in limited domains

A

unconstrained natural language is too difficult

86
Q

who created STUDENT and when

A

Bobrow (1967)

87
Q

who created SHRDLU and when?

A

T Winograd 1968-72

88
Q

first chatbot & created when

A

eliza, 1964-6

89
Q

who implemented PARRY and when

A

Kenneth Colby in 1972

90
Q

which is more sophisticated? eliza or parry

A

parry

91
Q

block worlds occurred primarily in which 3 domains

A

NLP, computer vision and robotics

92
Q

SHAKEY : developed when and where

A

Stanford 1966-72

93
Q

results of the SHAKEY project (3)

A

A* search algorithm, Hough transform (finding simple shape in images), Visibility graph method (used in robot motion planning)

94
Q

SHAKEY

A

First general -purpose mobile robot to be able to reason about its own actions

95
Q

SHAKEY used what to plan?

A

STRIPS

96
Q

STRIPS requires what 3 things

A

intial state, goal state and actions

97
Q

STRIPS develops…

A

a plan move from initital state to goal state by achieving appropriate subgoals

98
Q

in 1976, the world’s fastest supercomptuter was capable of how many MIPS

A

1000

99
Q

today, computer vision application require how many MIPs?

A

10^4 to 10^6 MIPS

100
Q

combinatorial explosion

A

(N) (sum) (n=0) k^n where k is the number of potential moves and N is the number of steps ahead that needs to be examined

101
Q

Moravec’s Paradox

A

high-level reasoning requires little computation effort but basic sensorimotor skills (e.g. perception/movement) are incredibly difficult to replicate

102
Q

Who created the perceptron?

A

Frank Rosenblatt (1957)

103
Q

the book Perceptrons was published by who when?

A

Minsky and Papert in 1969

104
Q

The Frame Problem

A

actions change specific things but everything else - “the frame” remains the same

105
Q

a single layer perceptron could not compute which function

A

the XOR

106
Q

Single layer perceptrons could only solve….

A

linearly seperable classification problems

107
Q

the qualification problem

A

the difficulty in specifying all possible pre-conditions for an action

108
Q

US ALPAC Report 1966

A

withdrawal of funding

109
Q

ALPAC purpose

A

appointed to evaluate progress in computational linguistics esp MT

110
Q

UK Lighthill Report 1973

A

AI researchers had failed to address the issue of combinatorial explosion

111
Q

US DARPA cancelled what at Carnegie Mellon University

A

Speech Understanding Research Programme

112
Q

the US N______ R_______ ______ also cancelled funding

A

National Research Council

113
Q

JR Lucas (1961) essentially reiterated

A

Turing’s anticipated Mathematical Objection

114
Q

Godel Incompleteness Theorem

A

any formal system has true statements it cannot prove within the system itself

115
Q

What did Lucas say about Godel’s Incompleteness Theorem?

A

a human can recognise the truth of these unprovable statements but a computer cannot

116
Q

according to Russell and Norvig, Godel’s argument only applies to

A

TMs since computers are only approximations of TMs (no infinite memory)

117
Q

Russell and Norvig’s 3 arguments to Lucas’ arguement

A

GIT only applies to systems powerful enough such as TMs, sentences which a given cannot consistently assert while others can,
cannot claim that humans aren’t subject to GIT

118
Q

2 books published by Hubert Dreyfus (and when?)

A

What Computers Cant Do (1972) and What Computers Still Cant Do (1992)

119
Q

Dreyfus advocated for which of Turing’s arguements

A

The Argument from Informality

120
Q

Argument from Informality

A

the human mind is not constrained by rigid, formal rules like a machine

121
Q

GOFAI

A

good old fashioned AI - all intelligent behaviour can be modelled by a system that reasons logically from a set of facts and rules

122
Q

DENDRAL developeed by who, when and where

A

Buchanan, Feigenbaum and Lederberg at Stanford

123
Q

one of the earliest expert systems

A

DENDRAL

124
Q

2 inputs to DENDRAL

A

mass spectometry data and the chemical compound of a molcule

125
Q

DENDRAL was powerful because what had been mapped?

A

theoretical knowledge needed to solve the problem

126
Q

DENDRAL marked a shift from

A

general reaonsing (weak methods) over axioms to experts’ rules that chunk large amounts of knowledge in the domain into specific rules

127
Q

DENDRAL was the first k____-i_____ system

A

knowledge-intensive

128
Q

knowledge intensive system

A

expertise stemmed from a large number of special purpose rules

129
Q

MYCIN (1972)

A

diagnose blood infections and recommended antibiotics/dosages

130
Q

True/False: Did MYCIN outperform junior doctors?

A

yes

131
Q

2 differences between DENDRAL and MYCIN

A

no general theoretical model from which MYCIN rules could be deduced and rules had to reflect uncertainty associated with medical knowledge

132
Q

what method did MYCIN use to address uncertainty and what COULD it have used?

A

used certainty factors, rather than Bayesian statistics

133
Q

why was MYCIN never deployed

A

ethical concerns and lack of electronic medical systems to integrate into

134
Q

knowledge acquisition bottleneck

A

the difficulty of acquiring and encoding expert knowledge into an AI system

135
Q

who argued about scripts?

A

Roger Schank

136
Q

what was Roger Schanks’ emphasis when he was arguing about scripts?

A

less emphasis on language itself and more on representing/reasoning with knowledge required for language understanding

137
Q

scripts

A

representations of stereotypical situations which are used to interpret stories about such situations

138
Q

Schank’s Script Applier Mechanism Program

A

could answer based on text inference and world knowledge

139
Q

scripts influenced which subdomain of applied NLP

A

information extracting/text mining

140
Q

frame

A

collections of facts, procedures and default values for an object type

141
Q

KL-One is an example of a

A

knowledge representation language

142
Q

why did knowledge representation languages emerge

A

to support the organisation of hierarchies of frames and inference over them

143
Q

knowledge representation languages were antecendants of what

A

OOP and description logics/ontologies/the semantic web

144
Q

knowledge based systems comprise which 2 sub-systems

A

knowledge base + inference engine

145
Q

inference engine

A

applies rules to a knowledge base to derive new facts/solve problems

146
Q

inference engine works over _____ -rules

A

if-then (implication)

147
Q

inference engines may use ….

A

forward or backward chaining

148
Q

expert systems

A

what KBSs were called in the business world

149
Q

first commercially successful KBS

A

R1 (later XCON)

150
Q

what did R1/XCON do?

A

configure newly ordered computers

151
Q

number of rules inR1/XCON

A

2500 rules

152
Q

True/False: R1/XCON was 95-98% accurate

A

true

153
Q

True/False: By 1998, most major US corps had Expert systems

A

True

154
Q

When was the return of research funding?

A

1980s

155
Q

how much did the UK govt put into the Alvey Project on IT

A

350 mil

156
Q

Good old Fashioned AI (LKRR)

A

early AI’s emphasis on logic, knowledge representation and reasoning

157
Q

3 paradigms developed in the mid 80s

A

Connectionism, intelligent agents, embodied/situated AI

158
Q

Connectionism revived…

A

neural network research

159
Q

key feature of Hopefield nets

A

recurrent - output from one unit can be fed back into itself via other units

160
Q

recurrent neural nets effectively have

A

internal memory

161
Q

recurrent neural networks can exhibit ….

A

dynamic temporal behaviour

162
Q

hopefield nets are best suited for

A

unsegmented, connected handwriting tasks

163
Q

RNNs use their internal memory to process…

A

arbitrary sequences of inputs

164
Q

back propagation

A

sends the error at the output back thru the net to adjust the weights of connections between neurons

165
Q

what would the ‘error’ be in terms of back propagation?

A

the difference between the network’s prediction and the actual result

166
Q

who popularised back-propagation

A

Rumelhart and McClelland in Parallel and Distributed Processing (1986)

167
Q

back propagation led to interest in…

A

deep learning

168
Q

embodied ai

A

To show real intelliegence, a machine needs to have a body (perception of the real world)

169
Q

which human ability does the embodied Ai approach claim is the least important?

A

abstract reasoning

170
Q

which human ability does the embodied Ai approach claim is the most important?

A

commonsense reasoning

171
Q
A
172
Q

who directly attacked the physical symbol system hypothesis?

A

Rodney Brooks in “Elephants Don’t Play Chess

173
Q

intelligent agent

A

an autonomous entity which observes through sensors and acts upon an environment using actuators and directs its activity towards achieveing goals

174
Q

the focus of an intelligent agent is on…

A

integrating skills (learning, language and vision) into a single entity that can perceive and act in an uncertain, dynamic environment

175
Q

internet bots are a type of…

A

intelligent agent

176
Q

3 principal paradigms

A

supervised, unsupervised and reinforcement learning

177
Q

supervised learning

A

labelled data where the

COM1005 - Machines and Intelligence (4 decks)

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