Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

CS3105 AI > 6: Tutorial stuff > Flashcards

6: Tutorial stuff Flashcards

1
Q

What does nCr expand to?

A

nCr = n! / r! * (n - r)!

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

What is a full joint distribution?

A

???

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

How do you find missing probabilities in full joint distributions?

A

???

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

What is a Bayesian network?

A

A dag map of probabilistic connections between probabilities such that an arrow points from a probability that is conditionally dependant on another to the othe

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

How do you build a Bayesian network?

A

???

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

How do you draw a Bayesian network?

A

???

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

What is a knowledge base (in logic)?

A

???

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

What are entailments?

A

???

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

When can you infer entailments?

A

???

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

What is a most general unifier?

A

???

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

What is a unifier?

A

???

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

What is unification?

A

???

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

What is substitution?

A

???

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

How does unification work?

A

???

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is the factoring rule?

A

???

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How does the factoring rule work?

A

???

17
Q

What is an 8-puzzle?

A

???

18
Q

What is NY taxi distance?

A

min non-diagonal node by node distance between two points on a graph (vertical and horizontal moves only)

19
Q

What is Manhattan distance?

A

min non-diagonal node by node distance between two points on a graph (vertical and horizontal moves only)

20
Q

What is backprop?

A

???

21
Q

How does backprop work?

A

???

22
Q

How does backprop relate to steepest gradient descent?

A

???

23
Q

How do you find the error-weight gradient for a unit behind a current hidden one, given its output (input into the current one)?

A

???

24
Q

How do gradients come to explode or vanish when the chain rule is applied to multiple hidden layers?

A

???

25
Q

What is the connection between validation and early stopping?

A

early stopping done to mainimise error in training/validation data to improve validation process

26
Q

What are hyperplanes?

A

???

27
Q

Where do hyperplanes rotate to from their initial setting when training is applied through back-propagation?

A

???

28
Q

What are convolutional neural networks?

A

Divide and conquer ish neural networks that convolute data to find patterns before recombining adjacent data into groups. often used in computer vision.

29
Q

How have convolutional neural networks helped recent breakthroughs in machine learning?

A

allowed advances in computer vision

30
Q

What is the difference in capability between a recurrent neural network and a feedforward network? Where does this difference arise from?

A

recurrent facilitates context and memory because of neurons being able to connect to themselves

CS3105 AI (8 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions