In the context of the 21st century and the fourth industrial revolution, the substantial proliferation of data has established it as a valuable resource, fostering enhanced computational capabilities across scientific disciplines, including physics. The integration of Machine Learning stands as a prominent solution to unravel the intricacies inherent to scientific data. While diverse machine learning algorithms find utility in various branches of physics, there exists a need for a systematic framework for the application of Machine Learning to the field. This review offers a comprehensive exploration of the fundamental principles and algorithms of Machine Learning, with a focus on their implementation within distinct domains of physics. The review delves into the contemporary trends of Machine Learning application in condensed matter physics, biophysics, astrophysics, material science, and addresses emerging challenges. The potential for Machine Learning to revolutionize the comprehension of intricate physical phenomena is underscored. Nevertheless, persisting challenges in the form of more efficient and precise algorithm development are acknowledged within this review.