Adaptive Neural Trees

07/17/2018
by   Ryutaro Tanno, et al.
0

Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures. We unite the two via adaptive neural trees (ANTs), a model that incorporates representation learning into edges, routing functions and leaf nodes of a decision tree, along with a backpropagation-based training algorithm that adaptively grows the architecture from primitive modules (e.g., convolutional layers). We demonstrate that, whilst achieving over 99 MNIST and CIFAR-10 datasets, ANTs benefit from (i) faster inference via conditional computation, (ii) increased interpretability via hierarchical clustering e.g. learning meaningful class associations, such as separating natural vs. man-made objects, and (iii) a mechanism to adapt the architecture to the size and complexity of the training dataset.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset