# NeuroView-RNN: It's About Time

arXiv: https://arxiv.org/abs/2202.11811 · HTML: https://mlsanity.com/paper/2202.11811/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 23 Feb 2022.

## Builds on (most cited first, 28 of 28)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations](https://mlsanity.com/paper/2002.04083/) (2020)
- [Learning from Failure: Training Debiased Classifier from Biased Classifier](https://mlsanity.com/paper/2007.02561/) (2020)
- [A Simple Way to Initialize Recurrent Networks of Rectified Linear Units](https://mlsanity.com/paper/1504.00941/) (2015)
- [Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks](https://mlsanity.com/paper/1706.05764/) (2017)
- [Interpretable and Steerable Sequence Learning via Prototypes](https://mlsanity.com/paper/1907.09728/) (2019)
- [The Recurrent Neural Tangent Kernel](https://mlsanity.com/paper/2006.10246/) (2020)
- [How to Construct Deep Recurrent Neural Networks](https://mlsanity.com/paper/1312.6026/) (2013)
- [Exploring Interpretable LSTM Neural Networks over Multi-Variable Data](https://mlsanity.com/paper/1905.12034/) (2019)
- [Human Trajectory Prediction via Counterfactual Analysis](https://mlsanity.com/paper/2107.14202/) (2021)
- [A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling](https://mlsanity.com/paper/1810.09050/) (2018)
- [SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties](https://mlsanity.com/paper/1712.02034/) (2017)
- [Explaining and Interpreting LSTMs](https://mlsanity.com/paper/1909.12114/) (2019)
- [Image Captioning with Deep Bidirectional LSTMs](https://mlsanity.com/paper/1604.00790/) (2016)
- [Interpretable Spatio-temporal Attention for Video Action Recognition](https://mlsanity.com/paper/1810.04511/) (2018)
- [Two Stream LSTM: A Deep Fusion Framework for Human Action Recognition](https://mlsanity.com/paper/1704.01194/) (2017)
- [Improving Interpretability of Deep Neural Networks with Semantic Information](https://mlsanity.com/paper/1703.04096/) (2017)
- [From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning](https://mlsanity.com/paper/1708.02478/) (2017)
- [Improving performance of recurrent neural network with relu nonlinearity](https://mlsanity.com/paper/1511.03771/) (2015)
- [Beat by Beat: Classifying Cardiac Arrhythmias with Recurrent Neural Networks](https://mlsanity.com/paper/1710.06319/) (2017)
- [RNN-based counterfactual prediction, with an application to homestead policy and public schooling](https://mlsanity.com/paper/1712.03553/) (2017)
- [A Comparison of Pooling Methods on LSTM Models for Rare Acoustic Event Classification](https://mlsanity.com/paper/2002.06279/) (2020)
- [Empirical Evaluation of RNN Architectures on Sentence Classification Task](https://mlsanity.com/paper/1609.09171/) (2016)
- [NeuroView: Explainable Deep Network Decision Making](https://mlsanity.com/paper/2110.07778/) (2021)

## Built on by (most cited first, 2 of 2)

- [TbExplain: A Text-based Explanation Method for Scene Classification Models with the Statistical Prediction Correction](https://mlsanity.com/paper/2307.10003/) (2023)
- [DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering](https://mlsanity.com/paper/2502.11509/) (2025)

## Abstract (arXiv)

Recurrent Neural Networks (RNNs) are important tools for processing sequential data such as time-series or video. Interpretability is defined as the ability to be understood by a person and is different from explainability, which is the ability to be explained in a mathematical formulation. A key interpretability issue with RNNs is that it is not clear how each hidden state per time step contributes to the decision-making process in a quantitative manner. We propose NeuroView-RNN as a family of new RNN architectures that explains how all the time steps are used for the decision-making process. Each member of the family is derived from a standard RNN architecture by concatenation of the hidden steps into a global linear classifier. The global linear classifier has all the hidden states as the input, so the weights of the classifier have a linear mapping to the hidden states. Hence, from the weights, NeuroView-RNN can quantify how important each time step is to a particular decision. As a bonus, NeuroView-RNN also offers higher accuracy in many cases compared to the RNNs and their variants. We showcase the benefits of NeuroView-RNN by evaluating on a multitude of diverse time-series datasets.