Machine learning is the science of making a computer act without programming. Deep learning is a subset of machine learning that, in very simple terms, can be thought of as the automation of predictive analytics.
How does it work?
Machine Learning uses algorithms to analyze data, learn from it, and then make a determination or prediction about something in the world. So instead of hand-coding software routines with a specific set of instructions to perform a particular task, the machine is “trained” using large amounts of data and algorithms that give it the ability to learn how to perform the task.
What is it for?
The purpose of machine learning is to discover patterns in your data and then make predictions based on those often complex patterns to answer business questions and help solve problems.
There are three types of machine learning algorithms:
1) Supervised learning
The data sets are labeled so that patterns can be detected and used to label new data sets.
2) Unsupervised learning
Data sets are not labeled and are sorted by similarities or differences
3) Reinforcement learning
The data sets are not tagged, but after performing an action or actions, the AI system receives feedback.
For example, if you provide a machine learning program with many x-ray images, along with their corresponding symptoms, it can help (or possibly automate) the analysis of x-ray images in the future.
The machine learning app will compare all those different images and find what the common patterns are in the images that have been tagged with similar symptoms. Also, when you provide new images, it will compare their content with the patterns it has collected and tell you how likely it is that the images contain any of the symptoms you have studied previously.