CH. 9 AI

Question 1

cognitive model

Answer 1

a computational system used to describe information processing aspects of cognition.

Question 2

turing test

Answer 2

a behavioral test of machine intelligence. If a machine communicating with a human judge via a text interface cannot distinguish it from a human, then the machine passes the test. Some believe that passing the Turing test is an adequate definition of machine intelligence.

Question 3

weak AI

Answer 3

the view that some machines can behave intelligently.

Question 4

strong AI

Answer 4

the view that at least some machines that behave intelligently really
are thinking.

Question 5

symbolic logic

Answer 5

an approach to automated reasoning in which knowledge is
encoded as sequences of symbols called sentences, and new knowledge arises by manipulating and recombining components of sentences according to a set
of formal rules.

Question 6

predicate calculus

Answer 6

a symbolic logic that supports the representation of general
knowledge about objects, properties, and relationships. Also called first-order
logic.

Question 7

computability theory

Answer 7

a formal account of computation, providing a means to discriminate between functions that can be computed and those that cannot.

Question 8

turing machine

Answer 8

an idealized machine equipped with an infinite memory that manipulates symbols in accordance with rules.

Question 9

algorithm

Answer 9

a finite sequence of formal instructions that can be executed by a
computer.

Question 10

computational theory of mind

Answer 10

the idea that the mind is a computational
system that converts sensory inputs into symbols and process these symbols in
accordance with rules in order to produce behavior

Question 11

symbolic systems/symbolic AI

Answer 11

an approach to AI that focuses on formal
rules applied to explicit symbol structures. This is the most popular computational
theory of mind and is closely related to the representational theory of mind. Associated with the view that the mind is to the brain as software is to hardware

Question 12

physical symbol system hypothesis

Answer 12

the claim that the ability of a machine to
manipulate symbolic structures is foundational for general intelligence. “A physical symbol system has the necessary and sufficient means for general intelligent
action” (Newell & Simon, 1976).

Question 13

sentential knowledge representation

Answer 13

an approach to knowledge representation inspired by sentences in natural languages. Propositions are represented as
sequences of symbols. Symbolic logic uses sentential knowledge representations.

Question 14

compositional knowledge representation

Answer 14

an approach to knowledge representation in which the meaning of a complex representation is a simple function
of the meanings of its parts.

Question 15

sound

Answer 15

a property of an automated reasoning system that guarantees that any
proposition inferred by the system is justified by the system’s body of knowledge.

Question 16

complete

Answer 16

a property of an automated reasoning system that guarantees that any proposition that is justified by a body of knowledge can be inferred by the
system when given that knowledge.

Question 17

locality

Answer 17

a property of automated reasoning systems using symbolic logic that
allows individual conclusions to be reached with certainty using only a small
amount of relevant knowledge.

Question 18

detachment

Answer 18

a property of automated reasoning systems using symbolic logic
that allows the justifications for conclusions to be discarded once the conclusions
are determined to be true

Question 19

truth-functionality

Answer 19

a property of automated reasoning systems using symbolic
logic that makes the meaning of a complex sentence a simple function of the
meanings of the components of the sentence.

Question 20

bounded rationality

Answer 20

automated reasoning that takes into account limitations on
computational resources such as memory and processing time

Question 21

heuristic

Answer 21

an approximate method that is not universally valid but may still support strong performance

Question 22

planner

Answer 22

an AI system that outputs action sequences expected to result in the
attainment of specified goals.

Question 23

frames

Answer 23

an approach to symbolic knowledge representation in which knowledge
concerning common situations (e.g., dining at a restaurant) is aggregated and
indexed by situation.

Question 24

semantic networks

Answer 24

an approach to knowledge representation using mathematical graphs, with nodes in the graph representing objects or concepts and
connections between nodes representing relationships.

Question 25

reasoning under certainty

Answer 25

automated reasoning when propositions are
believed to be true with graded levels of certainty.

Question 26

probability theory

Answer 26

a mathematical framework for describing stochastic processes and quantifying uncertainty.

Question 27

utility theory

Answer 27

a mathematical framework for describing and quantifying preferences between options. More preferred outcomes are associated with higher utility than less preferred outcomes.

Question 28

bayesian decision theory

Answer 28

the combination of probability theory and utility theory, providing mathematical methods for evaluating possible actions when there is uncertainty about the outcomes that will be produced by those
actions.

Question 29

expert systems

Answer 29

AI systems with capabilities associated with an area of professional expertise, such as medical diagnosis, financial market prediction, and
application of case law.

Question 30

knowledge-based systems

Answer 30

expert systems that depend upon domain-specific knowledge that is explicitly represented using symbolic structures, such as logical sentences

Question 31

functionalism

Answer 31

the view that mental states can be defined in terms of functional
relationships between sensory inputs, the internal states of a system, and behavioral outputs.

Question 32

multiple realization

Answer 32

in philosophy of mind, the view that types of mental states
can be realized in (that is, produced by) many different kinds of physical systems.
Desire and hunger are types of mental states that can be realized in human brains, octopus brains, computer hardware, etc.

Question 33

language of thought

Answer 33

a hypothesized system of mental representations with a structure that corresponds to the grammar of language. According to the language of thought hypothesis, cognition can be understood in terms of sentences unfolding in this mental language.

Question 34

productivity

Answer 34

the ability to produce an unlimited number of meaningful propositions.

Question 35

systematicity

Answer 35

the existence of regularities in the set of propositions considered
meaningful based on the compositional structure of the propositions.

Question 36

levels of analysis

Answer 36

distinctive ways to study the mind, focused on specific phenomena and using specific methodologies. In cognitive modeling, the neural level of analysis is often distinguished from the computational level of analysis, where the former is studied by neuroscience and the latter is studied by cognitive psychology.

Question 37

theoretical autonomy

Answer 37

the view, associated with symbolic AI, that the computational level of analysis need not draw on or be aware of developments
in the neural level of analysis, in the same way that software engineers need not be aware of how computer hardware works in order to write computer programs.

Question 38

connectionism

Answer 38

an approach to AI that is inspired by how the brain works; connectionism emphasizes the production of intelligent behavior by processing
inputs through the weights and connections of an artificial neural network that
is trained by exposure to inputs rather than being programmed.

Question 39

artificial neural networks

Answer 39

a kind of AI system inspired by the brain, involving large numbers of interconnected simple processing elements.

Question 40

graceful degradation

Answer 40

a property of AI systems in which performance declines only mildly in the face of small errors in the system or small amounts of damage.

Question 41

distributed representations

Answer 41

an approach to knowledge representation in
which the meaning of a representation depends on the pattern of activation over a collection of processing elements, in contrast to meaning being assigned
to the activation of individual processing elements.

Question 42

deep learning

Answer 42

an approach to machine learning that makes use of deep neural
networks.

Question 43

deep neural networks

Answer 43

artificial neural networks with a large number of successive layers of processing elements mediating between inputs and outputs.

Question 44

reinforcement learning

Answer 44

a framework for machine learning in which performance feedback only appears as infrequent rewards and punishments.

Question 45

deep reinforcement learning

Answer 45

an approach to machine learning involving
performance feedback in the form of infrequent rewards and punishments, incorporating deep neural networks.

Question 46

computational cognitive neuroscience

Answer 46

an approach to cognitive modeling that describes the information processing properties of cognition in terms of the
physical properties of the brain.

Question 47

cognitive architectures

Answer 47

formal frameworks for producing cognitive models, embodying commitments about cognition as constraints on the structure of such
models.

Question 48

Bayesian belief networks

Answer 48

a method for representing probabilistic relationships
between variables, supporting reasoning under uncertainty

Question 49

predictive processing

Answer 49

a theory of mind and brain according to which the brain maintains a system of internal models that constantly predict inputs (from
the external world or from other internal models). Errors between predicted and observed inputs are used to update the models, so that, over time, predictions become increasingly accurate. Neural and cognitive activity can be understood largely as constructions of these models.

Question 50

dynamical systems

Answer 50

systems with properties that change over time, often in complex ways. Dynamical systems theory provides formal tools for describing
and analyzing such systems.

Question 51

reactive control

Answer 51

an approach to robot control lacking explicit representations
of knowledge about the environment or about the effects of considered actions. Useful behaviors arise from the interplay between how the robot reacts to the sensed environment and how the environment responds to robot actions.

Question 52

explanatory pluralism

Answer 52

the view that different approaches to the study of cognition framed at different spatial and temporal scales and drawing on diverse methodologies can complement one another. Contrasted with theoretical autonomy