Machine learning, particularly neural networks, has impacted our daily lives, the tech industry, and even the scientific community. For example, machine learning algorithms have been applied for classification changes in physics: distinguishing a signal object from a background object or different types of signals. In this talk, I will introduce a technique called "Generalized Numerical Inversion" (GenNI) which is a technique for calibrating experimental/simulational data using neural networks. GenNI is particularly useful due to its simplicity and generalizability to multiple different variables of a given object. In the end, I will briefly summarize a recent progress in applying GenNI to collider physics data.