What is Machine Learning? How is Machine Learning related to Artificial Intelligence ?

Machine Learning is generally a subset of Artificial Intelligence which is used to build certain model based on the provided data. it is used to study the ability of a computer and and improvise itself from the past data and gained experience. Computational statistics, which focuses on making predictions using computers, are closely connected to a branch of machine learning, although not all machine learning is statistical learning. The study of mathematical optimization provides the field of Machine Learning with techniques, theory and application domains. A related area of research is data mining, which focuses on exploratory data processing by unsupervised learning.

Machine learning is generally divided into 3 categories:-

1) Supervised Learning-Supervised learning is the task of machine learning to learn a feature that maps an input based on example input-output pairs to an output. It infers a feature consisting of a collection of training examples from labelled training data.

2) Unsupervised Learning–Unsupervised learning is a form of Machine Learning that, in a data set without pre-existing labels and with a minimum of human oversight, looks for previously undetected patterns. Unmonitored learning , also known as self-organization, enables simulation of probability densities over inputs, in contrast to supervised learning that typically allows use of human-labeled data.

3) Reinforcement Learning–In order to optimise the principle of cumulative reward in Machine Learning, reinforcement learning (RL) is an field of machine learning concerned with how software agents can take action in an environment. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning.


Image Source:- Forbes.com

How is Machine Learning related to Artificial Intelligence ?

Machine learning has evolved out of the search for artificial intelligence as a scientific pursuit. Some researchers were interested in making machines learn from data in the early days of AI as an academic discipline. With different symbolic approaches, as well as what was then called “neural networks,” they tried to address the proble-m. These were mainly perceptrons and other models that were later found to be reinventions of the generalise-d linear statistical models. Probabilistic reasoning was also employed, especially in automated medical diagnosis.


Image Source:- Javapoint.com

Leave a Comment