2021 · 11 citations · 32 references
ComputingComputer ScienceFinanceArtificial IntelligenceClinical Decision SupportMachine LearningDecision TreesDeep LearningLoss FunctionNeural NetworksOverfittingRepresentation LearningDebuggingDeep Learning-based ClassificationInterpretabilityInterpretable Neural NetworksModel InterpretabilityNeural Network InterpretabilityNeural Network ModelingSurrogate Loss
Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use. In response, previous work combines decision trees with deep learning, yielding models that (1) sacrifice interpretability for accuracy or (2) sacrifice accuracy for interpretability. We forgo this dilemma by jointly improving accuracy and interpretability using Neural-Backed Decision Trees (NBDTs). NBDTs replace a neural network's final linear layer with a differentiable sequence of decisions and a surrogate loss. This forces the model to learn high-level concepts and lessens reliance on highly-uncertain decisions, yielding (1) accuracy: NBDTs match or outperform modern neural networks on CIFAR, ImageNet and better generalize to unseen classes by up to 16%. Furthermore, our surrogate loss improves the original model's accuracy by up to 2%. NBDTs also afford (2) interpretability: improving human trustby clearly identifying model mistakes and assisting in dataset debugging. Code and pretrained NBDTs are at https://github.com/alvinwan/neural-backed-decision-trees.
32
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
UCI Machine Learning Repository
Arthur Asuncion · Medical Entomology and Zoology · 2007 · 24.4K citations
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das et al. · 2017 · 21.6K citations
YOLO9000: Better, Faster, Stronger
Joseph Redmon, Ali Farhadi · 2017 · 19K citations
Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin · 2016 · 15.2K citations