Machine learning is one of the most influential and powerful technologies in the world today. More importantly, we are far from seeing its full potential. There’s no question, it will continue to make headlines for the foreseeable future. This article is designed as an introduction to Machine Learning concepts, covering all the fundamental ideas without being too high a level.
Machine learning is a tool for turning information into knowledge. In the last 50 years, there has been an explosion of data. This mass of data is useless unless we analyze it and find the hidden patterns in it. Machine learning techniques are used to automatically find valuable underlying patterns within complex data that we would otherwise have a hard time discovering. Hidden patterns and knowledge about a problem can be used to predict future events and make all kinds of complex decisions.
We are drowning in information and starving for knowledge – John Naisbitt
Most of us are unaware that we already interact with Machine Learning every day. Every time we Google, listen to a song or even take a photo, Machine Learning is becoming part of the engine behind it, constantly learning and improving from every interaction. It is also behind global breakthroughs such as cancer detection, the creation of new drugs, and self-driving cars.
The reason Machine Learning is so exciting is that it is one step away from all of our previous rule-based systems of:  if (x = y): do z
Traditionally, software engineering combined man-made rules with data to create answers to a problem . Instead, machine learning uses data and responses to discover the rules behind a problem. (Chollet, 2017)
Traditional programming vs Machine learning
To learn the rules that govern a phenomenon, machines have to go through a learning process by testing different rules and learning from their performance. Hence why it is known as Machine Learning.
There are multiple forms of Machine Learning; Supervised, unsupervised, semi-supervised, and reinforcement learning. Each form of machine learning has different approaches, but they all follow the same underlying process and theory. This explanation covers the general concept of Machine Tilt and then focuses on each approach.
A set of data examples, containing characteristics important to solving the problem.
A key driver of a problem that is powered by a machine-learning algorithm to help you learn.
The representation (internal model) of a phenomenon that a machine learning algorithm has learned from the data displayed to
Collect the data that the algorithm will learn.
Format and enter the data in the optimal format, extracting important features, and performing dimensional reduction.
Also known as the adaptive stage, this is where the Machine Learning algorithm really learns by showing you the data that has been collected and prepared.
You run the model to see how well it works.
Tune the model to maximize its performance.