How to define Machine Learning?

“A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.”

The Task, T

If we want a robot to be able to walk, then walking is the task.

“Learning is our means of attaining the ability to perform the task”

We could program the robot to learn to walk, or we could directly write a program that specifies how to walk manually.

Some of the most common machine learning tasks include the following:

  • Classification
  • Regression
  • Machine translation
  • Transcription

The Performance Measure, P

In order to evaluate a machine learning algorithm, we must measure its performance.

For tasks such as classification, we often measure the accuracy of the model.

Accuracy is just the proportion of examples for which the model produces the correct output.

The Experience, E

Machine learning algorithms can be broadly categorized as unsupervised or supervised by what kind of experience they are allowed to have during the learning process.

Unsupervised learning algorithms experience a dataset containing many features, then learn useful properties of the structure of this dataset.

Supervised learning algorithms experience a dataset containing features, but each example is also associated with a label or target.

How to define Machine Learning? was originally published in buZZrobot on Medium, where people are continuing the conversation by highlighting and responding to this story.

View at