Final

Question 1

Intelligence

Answer 1

Aggregate ability to achieve goals in the world, adapt to environment, mental self-governance

Question 2

Minsky cognitive revolution/AI

Answer 2

Importance of knowledge representation in machine so it can think;
Program would need terms for relations & ways of specifying hierarchical level;
Challenges of complex problem-solving: knowledge rep, perception, language & communication

Question 3

Debate nature of mental representations

Answer 3

Propositional (Pylshyn) vs Kosslyn & Schwartz visual imagery supported by map navigation & spatial transformation

Question 4

Turing’s role + goal

Answer 4

Universal Turing Machine + Turing test - can machines think?

Question 5

Grounding

Answer 5

Relationship exists b/t rep & referent eg sensory or H20=water;
Mental representations and decision making

Question 6

Intentionality

Answer 6

Link between representation and referent

Question 7

Symbol grounding problem

Answer 7

Symbols must be connected to environment to gain semantic quality. Use embodiment (sensors & effectors)

Question 8

Role of computation in cognitive science & AI

Answer 8

Mind performs computations on representations
Marr’s Tri-level Hypothesis: computational, algorithmic, implementational level

Question 9

Classical vs connectionist computing approaches

Answer 9

Formal systems view rule-based symbol manipulation independent of meaning
Connectionist knowledge as distributed patterns of activation, parallel processing
Dynamical view representations constantly adapt to new info

Question 10

Production rule

Answer 10

Rules used to perform operations required to get to solution;
If A then B

Question 11

Information processing approach

Answer 11

Automatic parallel processing + serial controlled thought

Question 12

Churchland’s neurocomputational theory

Answer 12

Most human knowledge should be understood in terms of activation of prototypes within connectionist frameworks

Question 13

Dennet’s multiple drafts model of consciousness

Answer 13

Sight/sound/touch streams processed in parallel, editing & awareness anywhere in stream

Question 14

ANN

Answer 14

Information processing, focus functionality, computer simulating operation of neurons

Question 15

Localist representations

Answer 15

Each node represents single concept/
Activation in single node (compare distributed representation among group of nodes)

Question 16

Semantic networks

Answer 16

Knowledge representation, focus abstract structure/relationships

Question 17

Spreading activation

Answer 17

Activity of one node spreads to related nodes, weakens as it moves through links
Help recall through multiple association

Question 18

Decentralized coordination

Answer 18

Information flow distributed among multiple nodes operating independently, agents rely on local data & interactions, greater flexibility, scalability, resilience

Question 19

Universal grammar

Answer 19

All human languages share common underlying structure, general principles + language-specific parameters

Question 20

Visual word form area and dyslexia

Answer 20

Activated more by pronounceable pseudo-words;
Dyslexia linked to reduced activation, lack automatic word recognition;
Application to educational practices: learning to read reshapes cortical networks

Question 21

Linguistic competence

Answer 21

Formal system overlooking language use/context

Question 22

Linguistic performance

Answer 22

Deviation from ideal former behaviour attributed to memory, processing capacity etc. How language used in real contexts

Question 23

Cannon-Bard theory of emotion

Answer 23

Subjective emotion and bodily arousal occur simultaneously

Question 24

Cognitive theory of emotion

Answer 24

Experience of emotion (physical + subjective) triggered by cognitive evaluation of event

Question 25

Social brain hypothesis

Answer 25

Large primate brains evolved to manage complex social groups, 2.5yo human child higher social intelligence score than chimpanzees & orangutans

Question 26

Tomasello & Carpenter 2005 chimpanzee RJA & IJA

Answer 26

Chimps show responding to joint attention but lack initiating JA

Question 27

Lieberman 2001 cognitive dissonance reduction

Answer 27

Preciously thought required conscious reasoning, but they used amnesiacs to show that behaviour-induced attitude change is fairly automatic, does not require explicit memory or processing

Question 28

Dual-attitude theory

Answer 28

Evaluative (amygdala threat assessment) vs nonevaluative (slow, semantic & associative processing)

Question 29

Choice blindness & biases

Answer 29

My side bias, confirmation bias

Question 30

Bottleneck theories

Answer 30

Explain selective attention/information filtering

Question 31

Treisman’s attenuator

Answer 31

Threshold effect: minimum activation required to produce conscious awareness, threshold determined by word’s meaning

Question 32

Multimode model of attention

Answer 32

Moveable filter depending on task demands, early sensory feature selection less demanding

Question 33

Wicken semantic memory interference

Answer 33

Words can interfere with recall of other words in same category eg apple/orange

Question 34

Heuristics

Answer 34

Rules of action most often leading to problem solution: Sub-goals, means-end analysis, diagram, analogy. Evaluation function to identify promising areas

Question 35

SOAR approach

Answer 35

State, Order, and Result: represents all tasks and problem space, follows decision cycle. Accumulate evidence/analyze problem, apply operator, evaluate outcome, generate subgoals. General problem solving applicable to many domains, dynamic learning adjusts to obstacles, mirrors real-word human decision-making. However, assumes unified memory structure

Question 36

Brute-force search

Answer 36

Trying all possible paths of solution tree; Problem: combinatorial explosion. Breadth-first search guaranteed to find shortest path, depth-first search may take many steps if deep solution

Question 37

EEG strengths

Answer 37

Orthogonally oriented neurons (cortical surface); High temporal low spatial resolution

Question 38

MEG strengths

Answer 38

Tangentially oriented (within folds); Good temporal and spatial resolution, OPM MEG room temp

Question 39

Contribution of 19th C phrenology

Answer 39

Brain organ with localized specific functions eg Broca & Wernicke’s area

Question 40

Samuel’s checkers program

Answer 40

Used pruning strategy, learned from experience instead of rules, play against self to improve

Question 41

Reason AI field has grown according to Stanford

Answer 41

Because lacks single, rigid definition

Question 42

Stuart Russell’s view on AI

Answer 42

Powerful but risky, can make high-quality decisions but may not share human values, advocating human-compatible AI instead of specific objectives

Question 43

Singularity

Answer 43

Lines between man and super intelligent machine blurred

Question 44

Pruning

Answer 44

Cut off unpromising paths (Samuel checkers)