Google Machine Learning Flashcards

Coursera

1
Q

What is Machine Learning?

A

It is a way to derive predictive insights from data.

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

What is Machine Learning

A

Machine learning is the subfield of computer science that gives “computers the ability to learn without being explicitly programmed.”

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

What are the 2 stages of Machine Learning?

A

Training and Prediction.

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

Questions to ask when framing a Machine Learning problem?

A

1) What is being predicted?
2) What data is needed?

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

Questions to ask when the Machine Learning is a question of software

A

3) What is the API for the problem during prediction?
4) Who will use this service? How are they doing it today?

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

What is the Data Problem to the Machine Learning question?

A

5) What data are we analyzing?
6) What data are we predicting?
7) What data are we reacting to?

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

Difference between Machine Learning, Artificial Intelligence and Deep Learning

A

AI components:
* Computer Vision
* Language Processing
* Creativity
* Etc.

Machine learning:
* Classification
* Clustering
* Neural Network
* Etc.

Revolution in Machine Learning:
* Deep learning

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

What is training serving skew?

A

it is a mismatch between the data or environment used during the training phase of a machine learning model and the data or environment encountered during the serving (or deployment) phase.

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