A Comparative Review- From Artificial Intelligence to Deep Neural Networks: Evolution, Architecture, Capabilities, and Applications

Abstract In moment’s digital and tech- driven world, terms like AI (Artificial Intelligence), ML (Machine Learning), DL (Deep Learning). These buzzwords are frequently used interchangeably, creating confusion about their true meaning. While they partake some parallels, each field also has its own unique characteristics. AI serves as the Broadview, encompassing conception, while ML learns retired patterns and connections from your data and focuses on developing algorithms that can help you prognosticate what will be next. DL is a technical subset of ML that uses Deep Neural Networks (DNNs) — networks with multiple retired layers to dissect data. The depth of the network allows it to automatically learn complex features from raw data, bypassing the need for mortal- engineered point birth. This paper presents a relative study of Artificial Intelligence (AI), Machine learning (ML) and Deep Learning (DL)on crucial generalities like elaboration infrastructures, capabilities, and operations.