CHAPTER 3 Flashcards

(11 cards)

1
Q

………………is a subfield of machine learning focusing
on learning data representations as successive layers of
increasingly meaningful representations.

A

Deep learning

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

……….. development of smart systems and machines that can carry out tasks that typically require human intelligence

A

AI

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

…………….Create algorithms that can learn from data and make decisions based on patterns observed

A

Machine learning

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

T/F *Deep Learning is effective at learning patterns without human intervention

A

T

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

Importance of Deep Learning for Computer

A

Deep learning has been a
game changer in the field
of computer vision.

*It’s widely used to teach
computers to “see” and
analyze the environment
similarly to the way
humans do.

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

Its applications on deep learning for computer vision

A

self-driven cars
robotics,
data analysis

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

Convolutional Neural Network (CNN) Structure

A
  • CONV: Convolutional kernel layer
  • RELU: Activation function
  • POOL: Dimension reduction layer
  • FC: Fully connection layer
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

……………….. is a neural network with some convolutional layers (and
some other layers).

A

CNN

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

T/F A convolutional layer has a number of filters that does
convolutional operation.

A

T

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

Why Pooling

A

Subsampling pixels will not change the object

We can subsample the pixels to make image smaller

fewer parameters to characterize the image

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

A CNN compressesa fully connected network by:

A

*Reducing number of connections
*Shared weights on the edges
*Max pooling further reduces the complexity

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