DeepAI AI Chat
Log In Sign Up

Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models

11/18/2016
by   Viktoriya Krakovna, et al.
Harvard University
0

As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks, state of the art models in speech recognition and translation. Our approach to increasing interpretability is by combining a long short-term memory (LSTM) model with a hidden Markov model (HMM), a simpler and more transparent model. We add the HMM state probabilities to the output layer of the LSTM, and then train the HMM and LSTM either sequentially or jointly. The LSTM can make use of the information from the HMM, and fill in the gaps when the HMM is not performing well. A small hybrid model usually performs better than a standalone LSTM of the same size, especially on smaller data sets. We test the algorithms on text data and medical time series data, and find that the LSTM and HMM learn complementary information about the features in the text.

READ FULL TEXT
07/09/2019

Improving the Performance of the LSTM and HMM Models via Hybridization

Language models based on deep neural neural networks and traditionalstoc...
08/09/2020

Comparative Analysis of the Hidden Markov Model and LSTM: A Simulative Approach

Time series and sequential data have gained significant attention recent...
07/09/2019

Comparing the Performance of the LSTM and HMM Language Models via Structural Similarity

Language models based on deep neural networks and traditional stochastic...
06/23/2016

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

Recurrent neural networks, and in particular long short-term memory (LST...
06/09/2019

LSTM Networks Can Perform Dynamic Counting

In this paper, we systematically assess the ability of standard recurren...
10/08/2021

Kinematically consistent recurrent neural networks for learning inverse problems in wave propagation

Although machine learning (ML) is increasingly employed recently for mec...