LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks

Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential input. Researchers interested in better understanding these models have studied the changes in hidden state representations over time and noticed some interpretable patterns but also significant noise. In this work, we present LSTMVis, a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics. The tool allows users to select a hypothesis input range to focus on local state changes, to match these states changes to similar patterns in a large data set, and to align these results with structural annotations from their domain. We show several use cases of the tool for analyzing specific hidden state properties on dataset containing nesting, phrase structure, and chord progressions, and demonstrate how the tool can be used to isolate patterns for further statistical analysis. We characterize the domain, the different stakeholders, and their goals and tasks. Long-term usage data after putting the tool online revealed great interest in the machine learning community.

[1]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[2]  Jürgen Schmidhuber,et al.  LSTM recurrent networks learn simple context-free and context-sensitive languages , 2001, IEEE Trans. Neural Networks.

[3]  Anne E Carpenter,et al.  Opportunities and obstacles for deep learning in biology and medicine , 2017, bioRxiv.

[4]  Fei Liu,et al.  Modeling Language Vagueness in Privacy Policies using Deep Neural Networks , 2018, AAAI Fall Symposia.

[5]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[6]  Phil Blunsom,et al.  Recurrent Continuous Translation Models , 2013, EMNLP.

[7]  Quoc V. Le,et al.  Semi-supervised Sequence Learning , 2015, NIPS.

[8]  Grzegorz Chrupala,et al.  Linguistic Analysis of Multi-Modal Recurrent Neural Networks , 2015 .

[9]  Wojciech Zaremba,et al.  Recurrent Neural Network Regularization , 2014, ArXiv.

[10]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[11]  O. Troyanskaya,et al.  Predicting effects of noncoding variants with deep learning–based sequence model , 2015, Nature Methods.

[12]  Grzegorz Chrupala,et al.  Lingusitic Analysis of Multi-Modal Recurrent Neural Networks , 2015, VL@EMNLP.

[13]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[14]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[15]  Kenney Ng,et al.  Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models , 2016, CHI.

[16]  Kwan-Liu Ma,et al.  Opening the black box - data driven visualization of neural networks , 2005, VIS 05. IEEE Visualization, 2005..

[17]  Xiaohui S. Xie,et al.  DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences , 2015, bioRxiv.

[18]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[19]  Zhen Li,et al.  Towards Better Analysis of Deep Convolutional Neural Networks , 2016, IEEE Transactions on Visualization and Computer Graphics.

[20]  Desney S. Tan,et al.  Interactive optimization for steering machine classification , 2010, CHI.

[21]  Fei-Fei Li,et al.  Visualizing and Understanding Recurrent Networks , 2015, ArXiv.

[22]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[23]  Ben Shneiderman,et al.  Strategies for evaluating information visualization tools: multi-dimensional in-depth long-term case studies , 2006, BELIV '06.

[24]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[25]  Xinlei Chen,et al.  Visualizing and Understanding Neural Models in NLP , 2015, NAACL.

[26]  Paulo E. Rauber,et al.  Visualizing the Hidden Activity of Artificial Neural Networks , 2017, IEEE Transactions on Visualization and Computer Graphics.

[27]  Yang Wang,et al.  rnn : Recurrent Library for Torch , 2015, ArXiv.

[28]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[29]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[30]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[31]  Chong Wang,et al.  Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin , 2015, ICML.

[32]  Jana-Rebecca Rehse,et al.  Predicting process behaviour using deep learning , 2016, Decis. Support Syst..

[33]  Erik F. Tjong Kim Sang,et al.  Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition , 2003, CoNLL.

[34]  Grzegorz Chrupala,et al.  Representation of Linguistic Form and Function in Recurrent Neural Networks , 2016, CL.

[35]  Yoshua Bengio,et al.  Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription , 2012, ICML.

[36]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[37]  Janet Wiles,et al.  Recurrent Neural Networks Can Learn to Implement Symbol-Sensitive Counting , 1997, NIPS.