Exam 3 Stuff

Front 1

Provide both definitions of Artificial Intelligence.

Back 1

The field that attempts to design an intelligent machine. An intelligent machine (an AI)

Front 2

Why do we think we can create AI?

Back 2

Functionalism: What makes something mind is not that it's made of, but how it functions. Mental states are physical states. Anything that can implement those physical states is a mind (nature of physical system doesn't matter).

Front 3

What is a computational task?

Back 3

One that follows a well-defined process/set of steps.

Front 4

What is an Algorithm?

Back 4

Sequence of instructions, effective procedure.

Front 5

What is the claim of AI?

Back 5

Cognitive tasks can be reduced to computational tasks.

Front 6

What is a node in an ANN?

Back 6

Units in network, they have activation values (numbers associated with that node). Also have thresholds, can fire if input exceeds threshold.

Front 7

What is a link in an ANN?

Back 7

Connection between nodes; have weights (number associated with that link)

Front 8

What values can a weight have in an ANN?

Back 8

between 1 and -1, closer to 1 or -1 = 'heavier' weight.

Front 9

What is the basis function for ANNs?

Back 9

Equation describing how inputs to node are calculated. Sj = (SUM)AiWji - Each connected node's activation value (Ai) multiplied by connection weight of link between the two nodes (Wji)

Front 10

What is an Activation function in an ANN?

Back 10

f(net): An equation describing how output affected by input.

Front 11

What is Backpropagation?

Back 11

Method of training ANN by gradually changing weights on links in response to feedback.

Front 12

What is the Backpropagation process? Step by step.

Back 12

Set all weights, Set target output for output nodes, Run ANN get actual output nodes, Subtract actual from target output(Error signal = target output - actual output), send error signal back through network.

Front 13

What is a Dynamical System?

Back 13

System that evolves over time in law-governed way.

Front 14

Define a State space.

Back 14

Geometrical space with as many dimensions as there are variables.

Front 15

How is cognition treated through the DST?

Back 15

Treated as outcome of set of interacting variables. Order emerges from chaos. Cognition = trajectory through state space.

Front 16

ANNs vs DST

Back 16

Complementary ways of modeling mind.

Front 17

Classical AI vs ANNs & DST

Back 17

Emphasis on setting initial conditions, letting system learn/evolve. Physical and social worlds have huge impact on cognition.

Front 18

How to get physical and social worlds into AI?

Back 18

Give Artificial mind Artificial body! i.e. Robotics

Front 19

What are the 3 building blocks of classical robotics?

Back 19

Sense, plan, act.

Front 20

How do robots sense?

Back 20

Sensors: Things that detect change in environment. Knowledge base: Specific info programmer gives system.

Front 21

How do robots act?

Back 21

Send control signal to actuators (parts of machine that move/ control a system) ex. Move wheels.

Front 22

How do robots plan?

Back 22

Use info from sense, generate task to execute. ex. go down.

Front 23

Explain sense, plan, act

Back 23

Compare current state to knowledge base/sensors, generate plan, execute plan, repeat.

Front 24

What is another approach to classical robotics?

Back 24

Subsumption architecture, get rid of planning, just sense and act.

Front 25

What is the uncanny valley?

Back 25

When graphing affinity & resemblance to human, don't see continuous increase, see large dip.

Front 26

How are ANNs, DST and robotics connected?

Back 26

Many robots use ANNs, DST. DST is current best proposal for embodied, distributed robotics and maybe human cognition?

Front 27

What is problem solving?

Back 27

Navigation through problem space to find solution. Usually: have initial, know/guess final state, guess intermediate states.

Front 28

What is a problem space?

Back 28

Mental representation of problem, including initial, final and possible intermediate states.

Front 29

Why can computers solve some problems much faster than humans?

Back 29

Mind is not a perfect machine.

Front 30

Why are some human problems hard for computers to solve?

Back 30

Many human problems aren't well-specified, don't come w/ finite set of instructions.

Front 31

Do external factors affect human problem solving?

Back 31

Yes. Messy vs. tidy work area. Chronotypes

Front 32

What are two different types of problems?

Back 32

Insight: solved suddenly with an AHA! moment.

Analytic, Use logic, trial & error, search through problem space.

Front 33

What is analogical reasoning?

Back 33

Using knowledge about one situation to reason about another situation.

Front 34

What is a relational pattern?

Back 34

Sameness acress two situations.

Front 35

What is mapping?

Back 35

Transferring info from one domain of experience to another.

Front 36

What are Target and Source when it comes to mapping?

Back 36

Source: Usually well understood, concrete, familiar, the thing you're using to understand the other thing. Target: Usually NOT well understood, abstract, the thing you're trying to understand.

Front 37

How are analogies written? How are they mapped?

Back 37

Target -> source, source -> target

Front 38

What is Inferencing?

Back 38

Making new conclusions based on mappings from source to target.

Front 39

What is Evaluating?

Back 39

Deciding which info Not to map (which inferences not to draw)

Front 40

Summary of Analogy

Back 40

Major method of problem solving for humans. We're better at it than computers. Sameness (relational patterns) in mind, not world.

Front 41

What is Design?

Back 41

Creating plan for the construction of an object or a system.

Front 42

Where do design failures arise from?

Back 42

Limited capacity of memory

– Performance affected by external factors (Tme of day, stereotypes, environment)

– Theory of mind (user & designer’s mental states don’t match)

– Distributed cogniTon (one person’s cogniTon clashes with another’s).

– Objects designed to support epistemic actions make thinking harder...

– Embodied understanding of objects not considered (bad handles)

Front 43

What are the 4 principles of good design?

Back 43

Have visible cues to operation of object (no false cues); Take advantage of affordances (knowledge about how an object can be used, interacted with, must treat cognition as embodied); If extra stuff (diagrams, instructions) needed, design has failed; Good design induces flow.

Front 44

What is flow?

Back 44

State of consciousness, characterized by intrinsic enjoyment, sustained attention, loss of self-consciousness, Presence: sense that you have left real world and are present in virtual world. Can apple to simple object, more often used for activity.

Front 45

What are some flow-inducing activities?

Back 45

The internet, games, writing a paper, debugging code, having a conversation, playing a game

Front 46

What are some properties that induce flow?

Back 46

Clear goal, challenges that match your skills, control over the task, immediate and efficient feedback. Bad design bad for flow.