Last minute repetition Flashcards

1
Q

Connectionism

A
  • Interconnected networks of simple units which work parallel to each other, connected by links
  • Consists of three layers: input, hidden and output units
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Constraint satisfaction

A
  • 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
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Differential Hebbian Learning

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Emotional Contagion

A

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

Can be linked to pattern association

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Types of human errors

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Simulated Annealing

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

SNIF-ACT

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Information foraging theory

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Machine Learning

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Stigmergy

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Neo-Hebbian Learning

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Turing machine

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

How does autoassociation work in the hippocampus?

A
  1. Dentate gyrus: Pattern seperation (helps transform similar inputs into distinct representations)
  2. CA3: Autoassociation (Pattern completion)
  3. CA1: Relaying processed information
How well did you know this?
1
Not at all
2
3
4
5
Perfectly