Neural Random Forests
This work addresses the need for more flexible and efficient predictive models in machine learning, though it appears incremental as it builds on existing random forest and neural network techniques.
The authors tackled the problem of combining the strengths of random forests and neural networks by reformulating random forests as neural networks, resulting in hybrid methods called neural random forests that showed excellent performance in various prediction problems with substantial numerical evidence.
Given an ensemble of randomized regression trees, it is possible to restructure them as a collection of multilayered neural networks with particular connection weights. Following this principle, we reformulate the random forest method of Breiman (2001) into a neural network setting, and in turn propose two new hybrid procedures that we call neural random forests. Both predictors exploit prior knowledge of regression trees for their architecture, have less parameters to tune than standard networks, and less restrictions on the geometry of the decision boundaries than trees. Consistency results are proved, and substantial numerical evidence is provided on both synthetic and real data sets to assess the excellent performance of our methods in a large variety of prediction problems.