recurrent neural nets Flashcards

1
Q

What are the applications of recurrent neural nets?

A
  • Speech recognition
  • Text recognition
  • Stock prices
  • Sequential data
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Vanilla supervised learning and Structured Input

A
  • vanilla supervised models (feedforward nets) assume no input structure. These models are not good for analyzing organized info like sentences
  • Doesn’t care about the order of the info
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

ways to model ordered sequences?

A
  • recursive functions. we want given a sequence input model it as a recursive function
  • First approach is to model the recursive function as a linear function and try to fit the weighs. Do this with minimized least squares sum. This is a linear regression
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Using keras for creating a recursive linear funtion

A
  • Use the dense layer with activation linear
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

logistic recursive sequence

A

s​1=α

s​2​​ =ws​1​​ −ws​1^2

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

What is windowing?

A
  • The process of processing the sequence for training

- Obtaining the input - output pairs

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

Flaws with FNN approach

A
  • The probabilistic interpretation of least squares is that input/output pairs are independent and identically distributed. This is not good because it means data don’t have structure
  • With iind changing a previous value the forward values don’t change
  • We make things independent the opposite we want
How well did you know this?
1
Not at all
2
3
4
5
Perfectly