Improving the expressiveness of deep learning frameworks with recursion

Abstract

Recursive neural networks have widely been used by researchers to handle applications with recursively or hierarchically structured data. However, embedded control flow deep learning frameworks such as TensorFlow, Theano, Caffe2, and MXNet fail to efficiently represent and execute such neural networks, due to lack of support for recursion. In this paper, we… (More)
DOI: 10.1145/3190508.3190530

Topics

13 Figures and Tables

Slides referencing similar topics