Last minute repetition

Question 1

Connectionism

Answer 1

• Interconnected networks of simple units which work parallel to each other, connected by links
• Consists of three layers: input, hidden and output units

Question 2

Constraint satisfaction

Answer 2

• Helps networks find stable patterns of activation that satisfy multiple interacting constraints
• Key to parallel distributed processing (PDP) models, where units adjust to reach a stable state

Question 3

Differential Hebbian Learning

Answer 3

A variant of Hebbian learning where weight changes depend on the temporal difference of pre- and postsynaptic activity.

Question 4

Emotional Contagion

Answer 4

Mechanism in which people aquire the emotions of others just by seeing their expression

Can be linked to pattern association

Question 5

Types of human errors

Answer 5

Slips and lapse: Errors committed in familiar situations, right plan but wrong execution
Mistakes: Errors committed in unfamiliar situations, choosing the wrong plan

Question 6

Simulated Annealing

Answer 6

Trying to escape a local minimum by adding noise, raising temperature, increasing energy and gradually cooling down to reach global minimum

Question 7

SNIF-ACT

Answer 7

Extension of ACT-R model, designed to mimic human psychology

Question 8

Information foraging theory

Answer 8

When humans search for information they try to maximize useful information while minimizing search effort. They look for information scents (utility) which determines whether or not something is worth pursuing.

The application of that is SNIF-ACT

Question 9

Machine Learning

Answer 9

Ability of computers to learn without being explicitly told what to learn (self-initiated)

Question 10

Stigmergy

Answer 10

Indirect communication by altering the state of the environment in a way that will affect the behavior of others

Can be connected to swarm intelligence

Question 11

Neo-Hebbian Learning

Answer 11

Restatement of hebbian learning, solving the provlem of constantly increasing weights caused by too many associations

Question 12

Turing machine

Answer 12

Mathematical model which can use a predetermined set of rules to determine a result from a set of input

Can be connected to ACT-R

Question 13

How does autoassociation work in the hippocampus?

Answer 13

1. Dentate gyrus: Pattern seperation (helps transform similar inputs into distinct representations)
2. CA3: Autoassociation (Pattern completion)
3. CA1: Relaying processed information