Sequence learning with recurrent networks: analysis of internal representations

By Joydeep Ghosh, Vijay Karamcheti. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Travers Ching
2. Edward Choi
3. Alexandr A Kalinin
4. Brett K. Beaulieu-Jones
5. Jimeng Sun
6. Daniel S. Himmelstein
7. Mohammad Taha Bahadori
8. Amr M. Alexandari

Citations in the corpus

• RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism (2016, background): “But The recurrence is on the attention generation components ( h i or g i ) while the hidden state v i is generated by a simpler more interpretable output. from use of RNNs is at the cost of model output that is notoriously difficult to interpret.”
• Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Early work by Ghosh and Karamcheti [355] used cluster analysis to study hidden states of comparatively small networks trained to recognize strings from a finite state machine.”
• Doctor AI: Predicting Clinical Events via Recurrent Neural Networks (2015, background): “Although, several recent attempts have been made to interpret the parameters of RNNs, such as [12] and this problem remains an active line of research [22, 7].”