Seven differences between academia and industry for building machine learning and deep learning models

An application with 95 percent accuracy may not behave much more differently than one with 96 percent accuracy. They are too expensive to train, too big to fit onto consumer devices, and too slow to be useful to users. In the research phase, you often do not care about the size of the model – but in real life you do. On what factors do you choose the baseline and how do you quantify it? Most of the time, in production, they are only useful if their performance is unquestionably superior.