The article provides a comprehensive review of the intersection between machine learning (ML) and physical sciences, highlighting recent research and applications. It begins by introducing fundamental concepts in ML, including supervised, unsupervised, and reinforcement learning. The review then delves into the application of statistical physics to understand ML methods, particularly in unsupervised learning, such as principal component analysis and Boltzmann machines. It discusses the use of ML in various physical domains, including particle physics, cosmology, quantum many-body physics, quantum computing, and chemical and material physics. The article also explores the development of novel computing architectures to accelerate ML processes and addresses the challenges and successes in these areas. Finally, it concludes with an outlook on future directions and potential advancements in the field.The article provides a comprehensive review of the intersection between machine learning (ML) and physical sciences, highlighting recent research and applications. It begins by introducing fundamental concepts in ML, including supervised, unsupervised, and reinforcement learning. The review then delves into the application of statistical physics to understand ML methods, particularly in unsupervised learning, such as principal component analysis and Boltzmann machines. It discusses the use of ML in various physical domains, including particle physics, cosmology, quantum many-body physics, quantum computing, and chemical and material physics. The article also explores the development of novel computing architectures to accelerate ML processes and addresses the challenges and successes in these areas. Finally, it concludes with an outlook on future directions and potential advancements in the field.