Hungarian Layer: Logics Empowered Neural Architecture Hungarian Layer: Logics Empowered Neural Architecture
Paper summary Since all algorithms can be modeled as multiple conditional branch operations, this paper allows you to incorporate conventional algorithms into neural networks by dynamically building the neural computation graph based on outputs of these algorithms. They obtain near SOTA on Quora Duplicate Questions and SQuAD without heavily fine tuning the architecture to each problem. One limitation is that the algorithm itself is not affected by the learning process and so cannot be learned. This method provides a nice way to incorporate non-differentiable code into differentiable computation graphs which can be learned via backprop like learning mechanisms.
arxiv.org
arxiv-sanity.com
scholar.google.com
Hungarian Layer: Logics Empowered Neural Architecture
Han Xiao
arXiv e-Print archive - 2017 via Local arXiv
Keywords: cs.CL

more

Summary by arjoonn 5 months ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and