Applying Code Vectors for Presenting Software Features in Machine Learning
Hyun-il Lim · 2018
Machine learning is a statistical approach to give machines the ability to learn with data, without being explicitly programmed. This approach is widely used in various areas with complex problems, such as image recognition, speech recognition, regression, classification, and prediction. The most important factor is how to express the characteristics of the data being analyzed. In this paper, we present code vectors as training data for presenting software features in software analysis, and give availability results for applying code vectors in machine learning approach for analyzing software through experiments with Java applications.