DecisioNet: A Binary-Tree Structured Neural Network. (arXiv:2207.01127v5 [cs.CV] UPDATED)

Deep neural networks (DNNs) and decision trees (DTs) are both
state-of-the-art classifiers. DNNs perform well due to their representational
learning capabilities, while DTs are computationally efficient as they perform
inference along one route (root-to-leaf) that is dependent on the input data.
In this paper, we present DecisioNet (DN), a binary-tree structured neural
network. We propose a systematic way to convert an existing DNN into a DN to
create a lightweight version of the original model. DecisioNet takes the best
of …

arxiv binary network neural network tree