Considerations for artificial intelligence and machine learning: Approaches and use cases

As data sets grow, leveraging machines to learn valuable patterns from structured data can be extremely powerful. The volume of data is too large for comprehensive analysis, and the range of potential correlations and relationships between disparate data sources are too great for any analyst to test all hypotheses and derive all the value buried in the data. Machine learning (ML) is ideal for exploiting the opportunities hidden in big data. Machine learning is a type of artificial intelligence (AI) that allows software applications to become more accurate in predicting outcomes without being explicitly programmed. The basics of machine learning is to build algorithms that can take input data and use statistical analysis to predict an output value within an acceptable range. This paper explores the basics of machine learning, discussing concepts and topics like supervised, unsupervised and reinforcement learning, regression, classification, model evaluation metrics, overfitting, variance versus bias, linear regression, ensemble methods, model selection, Decision Trees, Random Forests. The paper then will review several several use cases, where machine learning can be applied, including but not limited to Aerospace, Internet of Things (IoT) and Computer Network Analytics use cases. The applicability of AI and ML will be reviewed in these use cases. Finally, the latest trends in machine learning will be discussed.