Neural Networks Flashcards

1
Q

Beschreib Hebbs Rule

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

Beschreib den Aufbau eines Perceptrons

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

Wie lautet die Funktion der inner activation?

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

Wie funktioniert das Aktualisieren der Gewichte?

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

Wie minimiert man E?

A

Über das Gradientenabstiegsverfahren

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

Beschreib die Rule for the weights mathematisch

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

Wie funktioniert der Perceptron Algorithmus?

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

Wie funktioner lineare Separierbarkeit mir Perceptrons?

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

Was sind Sigmoid Neurons?

A

Haben folgende Aktivierungsfunktion

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

Why not choose all-same input weights for a layer?

A

all units will have same activations → information loss

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

Why not choose all-same output weights for a layer?

A

learning signals will be same → symmetry-breaking problem

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

Wie funktioniert Error Backpropagation?

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

Leite die Sigmoid Activation Function ab

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Beschreib Batch update

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Beschreib online update

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Beschreib Minibatch Updates

A
17
Q

Was ist der Momentum Term?

A