Humans become intelligent only through the learning process. This involves perceiving millions of things through our sensory organs. Similarly, for machines to become intelligent, we need to make them learn by providing a large amount of data, generally, known as big data. They can then be put through a learning process that makes use of various algorithms. This process is called machine learning. There are two different types of learning a machine can be put through:

• Supervised learning: In supervised learning, we provide a large dataset to the machine. Each input will be labeled with the expected output. Once the machine processes all the input data, the machine will be able to identify or classify a random input. For example, if we provide various pictures of a person as a dataset, the machine will be able to identify a new image of that person. Google's Face ID and Alexa's voice recognition are examples of supervised learning.
• Unsupervised learning: In unsupervised learning, machines are still fed with a large amount of data. However, each dataset is unlabeled. This means that for each data input, the outcome is unknown. The machine should be able to discover different patterns based on the data fed to it. For instance, in supermarkets, every time someone shops, their shopping list could be fed to a machine. Based on the input, the machine could be able to come up with a shopping pattern for the customer. Sometimes, the outcome will be a completely unknown pattern.