ML Algorithms

We now know that computers can "learn" from data.

We know there are different kinds of learning, and we need to strike a balance between over- and underfitting.

But we still don't understand how this learning occurs.

The answer? Machine learning algorithms. These are repeatable sets of instructions that let turn data into predictions.

The field is constantly evolving, but some well-known machine learning algorithms include:

• Linear Regression — trying to map training data (usually continuous data) to a straight-line function.
• Logistic Regression — similar to above, but the function has a discrete set of outputs (usually used for classification).
• Decision Trees — made by segmenting data according to branching paths of yes/no questions

But these algorithms vary from one another in important ways.

And to understand why, we need to discuss parameters.