A Scientometric Review of Machine Learning and Deep Learning Techniques
Dimple Kapoor, Deepali Gupta, Mudita Uppal
Abstract
Machine learning and deep learning has emerged as technological innovations transforming industries and changing landscape of the society. This review paper offers a comprehensive analysis of the present state of Machine Learning (ML) and Deep Learning (DL) as a burgeoning field, emphasizing its fundamentals, its workings and its types. Beginning with a literature review of ML and DL, this paper explores the core concepts underlying various ML techniques, including supervised, unsupervised, semi-supervised and reinforcement learning. This study also discusses relevant topics including issues such as data privacy, security and ethical considerations inherent in ML and DL development and applications. The scientometric analysis reveals a substantial rise in ML and DL papers during the previous ten years, indicating growing interest in the field with the maximum number of documents published in the year 2023. The findings underscore the rapid growth and dynamic nature of ML and DL fields, driven by advancements in computational power and the increasing availability of big data. By analyzing recent trends and the number of publications done in the past years, this paper provides important perspective into the evolving landscape of machine learning and deep learning and its impact on society.