A. What is machine learning?

Machine learning (ML) is the branch of science that deals with algorithms and systems performing specific tasks using patterns and inference, rather than explicitly programmed instructions. There are a variety of different use cases for machine learning, from image recognition to text generation. Most machine learning tasks generalize to one of the following two learning types:

  • Supervised learning: Using labeled data to train a model. The labels for the training dataset represent the class/category that each data observation belongs to. After training, the model should be able to predict labels for new data observations (from the same population distribution as the training data).

    • Example: Let’s say you’re training a machine learning model to predict whether a picture contains a lake or not. With supervised learning, you would train a model on a dataset of pictures where the label for each picture is “Yes” if it contains a lake or “No” if it doesn’t. After training, the model will be able to take in a picture and determine whether or not it contains a lake.

  • Unsupervised learning: Using unlabeled data to allow a model to learn relationships between data observations and pick up on underlying patterns. Most data in the world is unlabeled, which makes unsupervised learning a very useful method of machine learning.

    • Example: Going back to the same picture dataset from above, but now assume the training dataset is unlabeled. Using unsupervised learning, a model will be able to pick up on the inherent differences between pictures with a lake and pictures without a lake, e.g. differences in pixel color or orientation. This allows the model to cluster the pictures into two separate groups.

If it is possible to get large enough labeled training datasets, supervised learning is the way to go. However, it is often difficult to get fully labeled datasets, which is why many tasks require unsupervised learning or semi-supervised learning (a mix of supervised and unsupervised learning). Deciding which type of learning method to use is only the first step towards creating a machine learning model. You also need to choose the proper model architecture for your task and, most importantly, be able to process data into a training pipeline and interpret/analyze model results.