Learning Decision Trees Recurrently Through Communication
Integrated interpretability without sacrificing the prediction accuracy of decision making algorithms has the potential of greatly improving their value to the user. Instead of assigning a label to an image directly, we propose to learn iterative binary sub-decisions, inducing sparsity and transparency in the decision making process. The key aspect of our model is its ability to build a decision tree whose structure is encoded into the memory representation of a Recurrent Neural Network jointly learned by two models communicating through message passing. In addition, our model assigns a semantic meaning to each decision in the form of binary attributes, providing concise, semantic and relevant rationalizations to the user. On three benchmark image classification datasets, including the large-scale ImageNet, our model generates human interpretable binary decision sequences explaining the predictions of the network while maintaining state-of-the-art accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision Makingimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Ents: An Efficient Three-party Training Framework for Decision Trees by Communication Optimization
Multi-party training frameworks for decision trees based on secure multi-party computation enable multiple parties to train high-performance models on distributed private data with privacy preservation. The training proc…
Are crossing dependencies really scarce?
The syntactic structure of a sentence can be modelled as a tree, where vertices correspond to words and edges indicate syntactic dependencies. It has been claimed recurrently that the number of edge crossings in real sen…
SentenceAn Algorithmic Framework for Constructing Multiple Decision Trees by Evaluating Their Combination Performance Throughout the Construction Process
Predictions using a combination of decision trees are known to be effective in machine learning. Typical ideas for constructing a combination of decision trees for prediction are bagging and boosting. Bagging independent…
PredictionOn Ternary Coding and Three-Valued Logic
Mathematically, ternary coding is more efficient than binary coding. It is little used in computation because technology for binary processing is already established and the implementation of ternary coding is more compl…
General ClassificationYggdrasil: An Optimized System for Training Deep Decision Trees at Scale
Deep distributed decision trees and tree ensembles have grown in importance due to the need to model increasingly large datasets. However, PLANET, the standard distributed tree learning algorithm implemented in systems …
CPU