NDT: Neual Decision Tree Towards Fully Functioned Neural Graph

2017/12/16 by Han Xiao, Xiao, Han · 1 citation
Computer Science · #Advanced Neural Network Applications #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.1712.05934

openalex publication_date 2017/12/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Though traditional algorithms could be embedded into neural architectures with the proposed principle of \citexiao2017hungarian, the variables that only occur in the condition of branch could not be updated as a special case. To tackle this issue, we multiply the conditioned branches with Dirac symbol (i.e. 1_x>0), then approximate Dirac symbol with the continuous functions (e.g. 1 - e^-α|x|). In this way, the gradients of condition-specific variables could be worked out in the back-propagation process, approximately, making a fully functioned neural graph. Within our novel principle, we propose the neural decision tree (NDT), which takes simplified neural networks as decision function in each branch and employs complex neural networks to generate the output in each leaf. Extensive experiments verify our theoretical analysis and demonstrate the effectiveness of our model.

Citations

• ADADELTA: An Adaptive Learning Rate Method
• Gradient-based learning applied to document recognition
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Convexification of Neural Graph

Related

• Neural Decision Trees
• NBDT: Neural-Backed Decision Trees
• Neural Networks are Decision Trees
• A Survey of Neural Trees
• Gradient Boosted Decision Tree Neural Network