Recurrent neural networks and missing data

[michaelchughes]

Basic RNNs

Ch. 10: Sequence Modeling: Recurrent and Recursive Nets Goodfellow et al. https://www.deeplearningbook.org/

Accessible blog post

Chris Olah http://colah.github.io/posts/2015-08-Understanding-LSTMs/

Original LSTM paper

Hochreiter & Schmidhuber Neural Computation 1997 https://www.bioinf.jku.at/publications/older/2604.pdf

Original GRU paper

Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation Cho et al. EMNLP 2014 http://arxiv.org/abs/1406.1078

Original bidirectional RNN paper

Bidirectional recurrent neural networks Shuster & Paliwal IEEE Trans Signal Processing, 1997 https://ieeexplore.ieee.org/document/650093

Sample code for sequence classification

https://github.com/tufts-ml/time_series_prediction/tree/master/src/rnn

RNNs for Missing Data

Recurrent Neural Networks for Multivariate Time Series with Missing Values Che et al. Scientific Reports 2018 http://www.nature.com/articles/s41598-018-24271-9

Medical Applications of RNNs

Learning to Diagnose with LSTM Recurrent Neural Networks Lipton et al. ICLR 2016 https://arxiv.org/pdf/1511.03677.pdf

Multitask Learning and Benchmarking with Clinical Time Series Data Harutyunyan et al. http://arxiv.org/abs/1703.07771

Multi-scale RNNs

https://arxiv.org/abs/1609.01704 Hierarchical Multi-Scale Recurrent Neural Networks Junyoung Chung, Sungjin Ahn, Yoshua Bengio ICLR 2017

Semi-supervised RNNs

Johnson & Zhang ICML 2016 http://proceedings.mlr.press/v48/johnson16.html

[rathp]

Mortality Prediction and Palliative Care

Avanti & Andrew Ng IEEE 2017 Improving Palliative Care with Deep Learning (Stanford ML)

Medical Diagnostics With Deep Learning

Hannun, Rajpurakar & Andrew Ng Nature 2019 Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network

Shen & Andrew Ng IEEE 2016 Ambulatory Atrial Fibrillation Monitoring Using Wearable Photoplethysmography with Deep Learning