Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so.
Machine learning algorithms are readily available. For example, Python has many libraries which support these machine learning algorithms.
Using this we can:
- Import a data set
- Fit a model to the data set
- Find the accuracy (how well it predicts a new data point)
Then why to learn the basics when instead we can use the pre-built algorithms that are readily available?
Still, we should learn the basics (the mathematics behind these concepts) of machine learning to be able to take an informed decision about the performance of the model.
We can fit the model to a data set and get some performance, but how to justify whether the performance given by the machine learning algorithm is proper or not?
The design of experiment
To be able to take the decisions with confidence we should know the fundamental concepts.