Machine learning can be described as a part of AI which enables computers to learn new tasks and information automatically. This consists of developing models and algorithms that let computers draw conclusions or make forecasts from data patterns. Machine learning has gained popularity recently for its ability to handle datasets and make faster more accurate decisions compared to traditional methods. This paper discusses the comparison, between ML and DL, and the rise of ML in recent years and the increasing use of neural networks as well as the concepts of supervised and unsupervised learning.

Abstract The planning, construction, and upkeep of physical structures, including roads, bridges, buildings, and other types of buildings, are the primary responsibilities of civil engineers. Finding cracks and other flaws in structures is one of the more difficult tasks in the field of civil engineering. These flaws can put the structure's stability and safety at risk. A variety of structures, such as buildings, bridges, pipelines, and aircraft components, are all susceptible to developing cracks as a result of inherent flaws. Finding cracks is absolutely necessary in order to guarantee the structural soundness of these assets and guarantee their safety. In this article, we will investigate a variety of techniques and technologies that are utilized for crack detection, as well as the applications for each of these. The construction industry has long recognized the need of building fracture detection as a primary priority. Cracks can emerge in any part of a building, and their presence is typically indicative of problems with the structure or the foundation of the building. Finding these cracks early on is essential for ensuring the security and steadiness of buildings, not only during the construction period but also after they have been built and during their lifetimes. In this review essay, we examine a number of different strategies and methodologies that are utilized in creating crack detection, as well as the benefits, limitations, and difficulties associated with each.