Using inductive bias as a guide for effective machine learning prototyping
Nov 6 · 7 min read

What makes working on new machine learning (ML) use cases so exciting, and at times so frustrating, is ML’s lack of hard and fast rules. A few aspects of the model development process can be codified; for example, data should always be separated into strictly disjoint training and test sets to ensure that model performance isn’t attributable to overfitting. But…


