Machine learning types
Classification or Regression
Embeddings
100

Differentiate people and animals in a photo based on a repository of tagged photos

What is supervised machine learning?

100
Predict exactly how positive or negative tweets are

What is regression?

100

This variable indicates how many words to the left and to the right of the center word will be considered.

What is the window size?

200

Cluster students by learning style without previously knowing all the learning styles

What is unsupervised machine learning?

200

Decide on whether a sequence is positive, negative or neutral

What is classification?

200

Any function of this kind seeks to minimize the difference between prediction and gold label.

What is a loss function?

300

Predict a hidden word in a sentence without ever having seen exactly this sentence

What is self-supervised machine learning?

300

Identify handwritten numbers in the range of 0 to 9 and output the corresponding number

What is classification?

300
The process to provide feedback to the model on how much to update the weights.

What is backpropagation?

400

Recommend music based on previous choices of the user and known preferences

What is supervised machine learning?

400

Measure progression of diabetes based on features, e.g. body mass index, blood pressure, etc.

What is regression?

400

This is the most common type of optimization algorithm, also used in skip-gram.

What is (stochastic) gradient descent?