Traditional coding has been the bread and butter of developers since the dawn of computing. We're used to creating applications by breaking down requirements into composable problems that can then be coded against. However, machine learning is a new paradigm that is quickly changing the way we develop software.
In traditional coding, we express the rules of the application in a programming language. For example, if we're writing a game, we might code the rules for how the ball interacts with the bricks. However, in machine learning, we don't need to explicitly code the rules. Instead, we provide the machine learning algorithm with a set of examples and labels. The algorithm then figures out the rules for itself.
This is a powerful approach because it allows us to solve problems that would be difficult or impossible to code for explicitly. For example, we could use machine learning to develop a spam filter that learns to identify spam emails without any human intervention.
