Old Exam Part 2 New

Question 1

Connect each of the three game playing programs with exactly one of the

1. AlphaZero
2. AlphaGo
3. Deep Blue

a. has learned from expert games
b. searches all possible move sequences until a fixed depth
c. uses no expert knowledge at all

Answer 1

1c
2a
3b

Question 2

Bring the four phases of Monte-Carlo Tree Search in to their correct ord

Expansion
Selection
Backpropagation
Simulation

Answer 2

1. Selection
2. Expansion
3. Simulation
4. Backpropagation

Question 3

Choose the right answer

Assume you have a set of pictures of cats, and a set of pictures of dogs, and you use these to train a learning algorithm to recognize cats and dogs.

This problem is best described as:

a. reinforcement learning
b. semi-supervised learning
c. unsupervised learning
d. supervised learning

Answer 3

d. supervised learning

Question 4

Choose the right answer

In a game, each side can make 3 possible moves in each position. A machine performs an exhaustive look-ahead search for 4 plies (half moves). How many possible leaf positions will it consider?

a. 81
b. 32
c. 12
d. 64

Answer 4

a 81

Question 5

Given is a training example (x_1 ,x_2 ) = (1,-1) which should result in output 1. However, the network with the current weights and a threshold activation function outputs -1. How should the weights be changed:

w_0:
a. Increased
b. Decreased
c. Stay the same

w_1:
a. Increased
b. Decreased
c. Stay the same

w_2:
a. Increased
b. Decreased
c. Stay the same

Answer 5

w_0:
b. Decreased

w_1:
a. Increased

w_2:
b. Decreased

Question 6

Specify whether the following statements are true or false:

1. Retrograde analysis attempts to solve a game by computing the game-theoretic value of each possible game position.
2. It is not possible to write a chess program that always plays an optimal move, not even with unlimited memory and infinitely fast computation
3. The credit assignment problem describes the situation that an agent sometimes has to make sub-optimal actions in order to obtain information
4. A good machine learning algorithm tries to perfectly fit every point in the training dataset.

Answer 6

1 True
2 False
3 False
4 False