Neural Random Forest Imitation

arXiv:1911.10829v2 Announce Type: replace
Abstract: We present Neural Random Forest Imitation - a novel approach for transforming random forests into neural networks. Existing methods propose a direct mapping and produce very inefficient architectures. In this work, we introduce an imitation learning approach by generating training data from a random forest and learning a neural network that imitates its behavior. This implicit transformation creates very efficient neural networks that learn the decision boundaries of a random forest. The generated model is …

abstract architectures arxiv cs.lg data forests imitation learning mapping network networks neural network neural networks novel random random forests stat.ml training training data type work