Tip:
Highlight text to annotate it
X
Let's show some examples of machine learning problems
and I want you to tell me, for each one,
whether it's best addressed with supervised learning,
unsupervised learning,
or reinforcement learning.
And the first example is speech recognition--
where I have examples of voice recordings,
and then the transcript's intermittent text for each of those recordings;
and from them, I try to learn a model of language.
Is that supervised, unsupervised or reinforcement?
Next example is analyzing the spectral emissions of stars
and trying to find clusters of stars in dissimilar types
that may be of interest to astronomers.
Would that be supervised, unsupervised or reinforcement?
The data here would just consist of:
for each star, a list of all the different emission frequencies of light coming to earth.
Next example is lever pressing.
So--I have a rat who is trained to press a lever
to get a release of food
when certain conditions are met.
Is that supervised, unsupervised or reinforcement learning?
And finally, the problem of an elevator controller.
Say I have a bank of elevators in a building
and they have to have some program--some policy--
to decide which elevator goes up
and which elevator goes down
in response to the percepts,
which would be the button presses at various floors in the building.
And so, I have a sequence of button presses,
and I have the wait time that I am trying to minimize--
so after each button press, the elevator moves;
the person waiting is waiting for a certain amount of time,
and then gets picked up,
and the algorithm is, given that amount of wait time.
Would that be supervised, unsupervised or reinforcement?