The rapid development and success of information technologies has expanded the scope of its application in many scientific domains, including materials science. The traditional experimental, theoretical and computational techniques used in the field of materials science, has led to the generation of massive amount of data. This continuous generation of huge amount of materials’ data has sparked the era of “big” data-driven science. This has impacted the field of materials science in terms of the emergence of new field of materials informatics. The existing experimental and theoretical techniques find it challenging and expensive to process this massive amount of information and data available in the field of materials science. Machine learning, on the other hand, with its many algorithms and resources available makes the task of material processing and discovery more convenient and effective. In pursuit of finding better techniques, Deep learning has also been introduced to study the materials more effectively, leading to the discovery of several advanced materials. This area of deep materials informatics has opened new opportunities in the field of materials science, helping in the development and evolution of the world around us. This has initiated different fields, such as “Big Data”, “Data Science”, “Machine Learning”, and “Deep Learning” to come together to help in the extraction and processing of knowledge from data.