Machine Learning, often abbreviated as ML, is a subset of artificial intelligence where algorithms are designed to learn from data and make decisions or predictions. Unlike traditional programs, which include explicit instructions for what to do, machine learning algorithms learn from patterns in the data to make their own decisions.


Imagine, you’re learning to ride a bike. At first, you keep falling. But slowly, after falling a lot, you start to understand when to balance, how much to pedal, when to brake. That’s how Machine Learning works. Given data, it learns from it over time and gets better and better at figuring out the outcome on its own.

In-depth explanation

Machine Learning (ML) is a scientific discipline that explores the construction and study of algorithms that can learn from data. Such algorithms operate by building a model from example inputs and using that to make predictions or decisions, rather than following strictly static program instructions.

Machine Learning is closely related to and often overlapped with computational statistics, which focuses on making predictions using computers. It also has strong ties to mathematical optimization, which delivers methods, theory and application domains to the field. Machine Learning is sometimes conflated with data mining, where the two areas intersect.

ML is divided into three types according to the nature of the “signal” or “feedback” available to learning systems. These are Supervised learning, Unsupervised learning, and Reinforcement learning. Supervised learning includes both classification and numerical regression, which requires a human to label the input data. Unsupervised learning, on the other hand, deals with the hidden structure in unlabeled data. Lastly, reinforcement learning is a part of machine learning where an agent learns to behave in a environment, by performing actions and discovering errors or rewards.

A fourth type, semi-supervised learning, has been described, where parts of the sample inputs are often unlabeled, and clustering is used for data analysis. Deep Learning is a type of Machine Learning that structures algorithms in layers to create an artificial neural network that can learn and make decisions on its own.

Machine Learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, speech recognition, image recognition, and computer vision, where it is difficult or infeasible to develop conventional algorithms to perform the needed tasks.

Machine Learning is an expansive discipline, and as it progresses, we will witness it solving a wide range of complex problems across a multitude of industries in the coming years.

Supervised Learning, Unsupervised Learning, Reinforcement Learning (RL),, Deep Learning, Artificial Neural Networks, Feature Extraction, Training Set, Test Set, Bias-Variance Trade-off, Regression, Classification, Clustering, Semi-Supervised Learning```