The creation of hardware and software with intelligence that mimics human behaviour is the focus of the branch of computer science known as artificial intelligence (AI). Computers designed with artificial intelligence are capable of recognizing speech, learning, problem-solving, and planning, among other things. One of the most deadly infections, pneumonia can swiftly cause major damage to the lungs. An infection of the lungs, either bacterial or viral, causes it. A effective course of treatment depends on an early diagnosis. In order to diagnose chest X-rays and simplify the pneumonia diagnosis process for both experts and novices, there is a need for an intelligent and autonomous system. There are models for xray imaging-based methods of pneumonia diagnosis and identification that are quick and straight forward. The goal of this study is to create a model that will help in classifying chest x-ray images into normal (healthy) and abnormal conditions (sick).Seven state-of-the-art machine learning techniques have been applied to improve accuracy and efficiency, in addition to well-known convolutional neural network models. This article reviews the techniques and approaches for utilizing deep learning to build a model for pneumonia detection. In order to help the chest doctor make decisions quickly, accurately, and conveniently, it is important to find a reliable and effective way to diagnosis pneumonia using X-rays. Annotated datasets were accessible and provided as a testing ground for machine learning techniques. They are performing numerous imaging-related jobs in the medical field. Pneumonia is the leading cause of death in children under five worldwide, accounting for more than 15% of all fatalities. Here, we describe a machine learning-based approach to detecting and localizing pneumonia in chest X-ray images (CXRs). However, you require specialized expertise and experience to appropriately read the X-ray images.