RNNVis: Understanding Hidden Memories of Recurrent Neural Networks

Yao Ming, Shaozu Cao, Ruixiang Zhang, Zhen Li, Yuanzhe Chen, Yangqiu Song, and Huamin Qu



RNNVis is a visual analytics tool for understanding and comparing recurrent neural networks (RNNs) for text-based applications. The functions of hidden state units are explained using their expected response to the input texts (words). It allows users to gain more comprehensive understandings on the RNN's hidden mechanism through various visual techniques.


To appear in Proceedings of VAST 17. [preprint]


[VIS17 Preview]



RNNVis is under development. A working demo can be found here. If you have any comments or suggestions, feel free to open an issue.


This project has used the following dataset: