← Back to Glossary

What is Machine Learning?

by Iwan Price-Evans on Machine Learning • May 31, 2022

Machine learning is a way for computers to learn without being explicitly programmed. It allows computers to recognize patterns in data and then use those patterns to classify new data.

What Is Machine Learning?

Machine learning is a type of artificial intelligence (AI) that uses statistical methods to ingest and analyze data, identify patterns, apply classifications, and make predictions based on what has been learned.

Data engineers can use machine learning to power task automation, learn new information, and create self-improving systems.

The History Of Machine Learning

Machine learning was first developed by John McCarthy at Dartmouth College in 1955. He coined the term “artificial intelligence” because he believed that machines would eventually surpass human intelligence. However, machine learning is not the same as AI. While both involve pattern recognition, AI involves more complex reasoning than just identifying patterns.

How Does Machine Learning Work?

Machine learning is an approach to computer programming in which the goal is to create algorithms that allow computers to identify patterns in very large datasets in an ongoing manner. These machine learning algorithms are designed to ingest data continuously and to revise their behavior as new patterns are identified and accommodated.

In traditional computer programming, decision-making is executed according to static commands that only the programmer can alter. In the machine learning paradigm, decision-making logic is dynamic and the algorithm can alter the logic itself without any intervention on the part of the programmer. As an ML algorithm processes more data, it can identify patterns in more detail and adjust its behavior accordingly.

For example, an algorithm intended to identify dogs in a video will be able to identify variation among dogs with greater accuracy as it analyzes more videos containing dogs of different breeds. If the dog recognition algorithm analyzes only videos with Labradors, it will only be able to identify dogs that look like Labradors. However, as its “learning logic” is applied to an expanded array of videos with many different breeds of dogs, it will expand its general understanding of dogs to include the traits of all the breeds it is exposed to. The algorithm will change its behavior. It will identify collies as dogs, chihuahuas as dogs, and bullmastiffs as dogs.

The ML algorithm is not born knowing what a dog is; it has to use its dataset to construct a model that accurately and comprehensively describes a dog. The more data processed, the better the model.

Types Of Machine Learning Algorithms

There are two main categories of machine learning algorithms: supervised learning and unsupervised learning.

Supervised learning requires training data, where examples of known outcomes are provided along with the correct answers.

Unsupervised learning does not require training data, so it is often used when there is no clear answer to what should happen next.

Applications Of Machine Learning

Machine learning is used by Apple, Google, Facebook, and others for automated image recognition, enabling photo libraries to recognize human faces, plants, animals, and other objects.

Machine learning is used in business applications such as fraud detection, lead scoring, customer service, and recommendation systems. These applications use statistical techniques to analyze large amounts of data and make predictions based on past behavior.

Machine learning is used in healthcare to identify patterns in public health and to power diagnostic AI.

Machine learning is used in cyber security for threat intelligence, bot detection, cloud abuse detection, and security automation. 

Conclusion

Machine learning is a powerful technology that allows us to automate tasks that would otherwise require human intervention. This automation will continue to improve our lives by allowing machines to perform more complex tasks than ever before.