Explainable AI: Physics in Machine Learning?

In trying to describe phenomenon in the real world, we would need to build models that can closely replicate these events. In general, most modeling approaches could be grouped into two main categories: data-driven or theory-driven solutions. Data-driven approach relies on using data to make sense of the phenomenon around them, but often with limited understanding of the underlying theoretical explanation. For instance, you are told to predict the housing price in a particular neighborhood. You have a good working hypothesis to work with, such as, the size and distance to popular service amenities will have some bearing to the housing price.