NBDT swMATH ID: 42496 Software Authors: Alvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Henry Jin, Suzanne Petryk, Sarah Adel Bargal, Joseph E. Gonzalez Description: NBDT: Neural-Backed Decision Trees. 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 Homepage: https://arxiv.org/abs/2004.00221 Source Code: https://github.com/alvinwan/neural-backed-decision-trees Dependencies: Python Related Software: COVAREP; RUBi; OpenFace; VL-InterpreT; CLEVR; MDETR; ViLT; VisualBERT; MultiBench; ViLBERT; DIME; GloVe; Flickr30K; Grad-CAM; Faster R-CNN; VQA; LXMERT; iMotions; Python; MultiViz Cited in: 0 Publications