Deep Learning in Finance Lect7 Flashcards

1
Q

Deep Learning led to the concept of?

A

Artificial Neural Networks - using layers of artificial neurons to receive input and apply an activation function along with a human set threshold.

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

In single layer neural network, there consists what factors?

A
  1. model inputs - multiple real numbers,
  2. Weights, which connect inputs to unit
  3. Single model unit
  4. Output
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Model inputs in Single Layer neural networks are usually associated with

A

real numbers

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

Explain the importance and detail of weights

A

Weights need high computational power to optimize “w” values, connect input to model to output

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

Output is in Single Layer Neural Networks consist of?

A

Weighted sum of inputs plus a bias term b, only achieved when input exceeds a threshold

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

3 common activation functions

A

Identity: f(a) = a
(upwards straight line)
Sigmoid: f(a) = 1/ 1+e^-a (curve)
ReLu: f(a) = max(0,a)

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

Hidden layer is the act of?

A

Misdirecting weights to another layer

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

Neural network

A

Parametreized family of non-linear functions

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

Types of Neural network

A
  1. feed forward (acyclic) - single-layer or multi-layer
  2. recurrent (cyclic)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Key Idea of Neural network Learning

A

Adjusting the weights, changes the function represented by the neural network
(learning = optimisation in weight space)

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

Difference between target output and network output

A

Iteratively adjust weight to reduce error

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

Anything in between input and output layer is called

A

Hidden layer

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