After your graduation, you move to the beautiful city of York, and a few weeks later you decide that the Blue Bicycle is your favourite local restaurant. Since then you always eat in Blue Bicycle. Which statements could describe this situation using the reinforcement learning terminology? (Exactly two answers are correct.)

What is the dot product between the following two vectors and ?

The Q-value quantifies the quality of an action in the state .

The Q-learning update equation (given below) returns a new value for the current state using the current reward and the value of the best action in the next state.

The following lists are defined in Python:

w1=[4, 6, 4,3]

w2=[5, 2, 6, 9]

and then the following dot product is computed:

np . d o t ( w1 , w1) 

If this dot product computes the similarity between two words, what is the dimensionality of their word embeddings?

Reinforcement learning algorithms are given numerical feedback, known as reward or reinforcement, but they must determine "on their own" how to maximise this reward.

Select one statement about attention and dot products that is correct.

Masked attention in a standard GPT allows the word at position N to attend to all previous words at positions N-1, N-2, etc.

Match the concepts with their characteristics or intended use.

The following image of a Transformer is presented:

What does the acronym MLP correspond to or what does it mean or what does it refer to?