Chapter 7 - Knowledge

Question 1

concept

Answer 1

unit of knowledge

mental representation that picks out a set of entities

Question 2

Category

Answer 2

group of related things

-concepts link knowledge together

Question 3

Categorization

Answer 3

process by which things are placed into groups called categories
understanding, prediction, learning, communication

Question 4

Definitional approach (categorization)

Answer 4

determine category membership based on whether the object meets the definition of the category
-can work for certain abstract/constructed categories

Question 5

Defining features (categorization)

Answer 5

features that any object MUST have to be a category member

-necessary and sufficient conditions

Question 6

Prototype approach (categorization)

Answer 6

• family resemblance

- things in a category resemble one another in a number of ways

Question 7

Prototype (categorization)

Answer 7

an average of category members encountered in the past

• an abstract representation of the typical member of a category
• not an actual member of the category

Question 8

Characteristic features (categorization)

Answer 8

• features that objects in the category typically have
• the most salient features of category
• true of most instances in category

Question 9

Exemplar approach (categorization)

Answer 9

• actual examples of the category (members)
• concept is represented by multiple examples
• to categorize, compare the new item to stored examples

Question 10

typicality effect

Answer 10

more typical members of a category are processed faster and easier
-apple is a fruit vs pomegrranate is a fruit

Question 11

Cognitive economy (semantic network)

Answer 11

shared properties are only stored at higher-level nodes

Question 12

Inheritance (semantic network)

Answer 12

lower level items shared properties of higher level items

-robin has feathers

Question 13

connectionism

parallel distributed processing (PDP)

Answer 13

-computer models for representing cognitive processes

loosely based on neurons and neural networks

Question 14

Units

connections

Answer 14

• neurons in layers

- synapses between units

Question 15

Output layer
hidden layers
input layer

Answer 15

• receive input from hidden layers, provide resulting signal from network
• receive input from input and hidden layers, send output to hidden and output layers
• activated by stimulation from environment, send signals to hidden layers

Question 16

connection weight

Answer 16

strength of connection between two units

• determines how strongly an incoming signal will activate the next unit
• changes in connection weights happen slowly and represent learning and memory

Question 17

activation

Answer 17

represents how active the neuron currently is

-changes in activation happen quickly and represent moment to moment info processing

Question 18

error signal

Answer 18

difference between actual activity of each output unit and correct activity

Question 19

backpropagation

Answer 19

algorithm to update connection weights based on error signal
-updating starts at the output units and works backwards toward input units

Question 20

learning

Answer 20

properties are correctly assoicated with concepts

Question 21

similarity

Answer 21

similar concepts (with similar properties) share similar representations (patterns of activation)

Question 22

generalization

Answer 22

knowledge is shared among similar concepts

Question 23

graceful degradation

Answer 23

performance decreases gradually as more and more of the network is damaged