Machine learning architecture and framework

Abstract Machine Learning (ML) is a branch of Artificial Intelligence that enables computer systems to learn from past experiences and improve accordingly without the direct intervention of the programmer. ML enables machines to behave very similarly to human beings. In order to extract the required information from the huge amount of data, ML can be used to design algorithms based on the trends of data and relationships among the data. ML can be applied in various fields such as intrusion detection, bioinformatics, health care, marketing, game playing, and so on. It enables the computers or the machines to make data-driven decisions rather than being explicitly programmed for carrying out a certain task. These programs or algorithms are designed in a way that they learn and improve over time when they are exposed to new or unseen data. Due to the huge amount of data, the significance of ML can be seen in various sections of the society. Especially in industries, ML is assisting exploration of the hidden patterns of the data, and through this the overall performance of the business can be improved. It is cost-effective, affordable, and simple computing techniques allow the analysis and handling of a huge amount of complex data. ML is not only helping to understand and identify the hidden patterns of a diverse set of data but also encourages automation in analysis in place of humans. Also, ML is helping industries to avail of the opportunities and make it profitable in future endeavors. In this chapter, we first review the fundamental concepts of machine learning such as feature assessment, unsupervised versus supervised learning, and types of classification. Then, details of the ML architecture and framework are discussed.