Skip to yearly menu bar Skip to main content


Poster

Adaptive Neural Trees

Ryutaro Tanno · Kai Arulkumaran · Daniel Alexander · Antonio Criminisi · Aditya Nori

Pacific Ballroom #82

Keywords: [ Architectures ] [ Ensemble Methods ] [ Representation Learning ] [ Supervised Learning ]


Abstract:

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 competitive performance on classification and regression datasets, ANTs benefit from (i) lightweight inference via conditional computation, (ii) hierarchical separation of features useful to the predictive task 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.

Live content is unavailable. Log in and register to view live content