Lecture 10 - Intro to Machine Learning Flashcards

1
Q

Why is machine learning a big thing?

A

Extremely difficult for computers to do very simple human tasks

4 year old outperforms computer every time at distinguishing dogs from cats

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

What is machine learning?

A

Branch of AI concerned with making computers learn from experience/data

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

What was Lady Lovelace’s Objection?

(sure we’ve had this before but meh)

A

“Computers cannot be intelligent because they only do what the programmer tells them to”

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

What is Turing’s response to Lovelace’s objection?

A

We can program computers to learn and think.

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

What did Arthur Samuel build in 1950s? Why is it important to AI?

A

Checkers/Draughts playing program that improved performance the more it played and reached state championship level

Important because one of the first machine learning programs

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

When were the first neural network systems?

A

Mid 1950s-Early 1960s

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

What are the Key Elements of a Machine Learner?

A

Task

Performance Measure

Set of Examples

Representation format for examples

(Models/Algorithms for learning)

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

How can learning be represented as a search?

A

Search of the space of possible representations of a model that maximises the performance measure:

y = f (x, W)

where f = model structure, W = model parameters

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

What are the 4 main types of learning?

A

Learning to Classify - e.g. learning to categorise animals based on pictures

Learning to Predict Numeric Values (regression/approximation)

Learning to form groups - making unclassified data make sense in some way

Learning what to do next - supervised learning - e.g. playing checkers

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

What type of learning is decision tree induction?

A

Learning to Classify

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

What type of learning do Neural Networks undertake?

A

Learning to Predict or Classify

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

If two events are statistically independent (i.e. neither one helps you predict the other) then

P(X ^ Y) = ?

A

P(X) x P(Y)

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

If P(X ^ Y) != P(X) x P(Y) then we can conclude that

A

Knowledge of one event can help you predict the other

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

P(X|Y) can also be represented:

A

P(X^Y) / P(Y)

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