In this section, we will try to define machine learning from computer science, statistics, and data analytical perspectives. Machine learning (ML) is the branch of computer science that provides the computers the ability to learn without being explicitly programmed (Arthur Samuel in 1959). This field of study being evolved from the study of pattern recognition and computational learning theory in artificial intelligence.

More specifically, ML explores the study and construction of algorithms that can learn from heuristics and make predictions on data. This kind of algorithms overcome the strictly static program instructions by making data-driven predictions or decisions, through building a model from sample inputs. Now let's more explicit and versatile definition from Prof. Tom M. Mitchell, who explained what machine learning really means from the computer science perspective:

Based on that definition, we can conclude that a computer program or machine can:

• Learn from data and histories
• Be improved with experience
• Interactively enhance a model that can be used to predict the outcomes of questions

Typical machine learning tasks are concept learning, predictive modeling, clustering, and finding useful patterns. The ultimate goal is to improve learning in such a way that it becomes automatic so that no human interactions are needed anymore, or to reduce the level of human interaction as much as possible. Although machine learning is sometimes conflated with Knowledge Discovery and Data Mining (KDDM), but KDDM, focuses more on exploratory data analysis and is known as unsupervised learning. Typical machine learning applications can be classified into scientific knowledge discovery and more commercial applications, ranging from Robotics or Human-Computer Interaction (HCI) to anti-spam filtering and recommender systems.