Want To Simplify Neural Networks? Transform Them Into Decision Trees

The applications of deep learning are growing so vast that it has made a great headway into areas requiring heavy computing. And, the elements that make up DL models — artificial neural networks (ANN) — can be said to be the driving force behind the subject. Neural networks can perform tasks efficiently, especially those related to classification. But, the problem lies in its understanding, meaning that neural networks are incomprehensible when it comes to their function. It is not yet ascertained as to why it performs classification so well. This article elaborates on a research paper by noted computer scientists Geoffrey Hinton and Nicholas Frosst, where they go in-depth about how a neural net can be made into a soft decision tree. Interpretation Through Decision Trees In the