International Conference for Learning Representations (workshop track)

By Ivan Titov, Ehsan Khoddam. 2015

How researchers see this paper

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

1. Finale Doshi-Velez
2. Viktoriya Krakovna
3. Adrian Weller
4. Been Kim
5. Menaka Narayanan
6. Isaac Lage
7. Yinjun Wu
8. Nicolas Papernot

Citations in the corpus

• Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models (2016, methodology): “Karpathy et al. (2016) showed that some LSTM cell states can be interpreted with the naked eye by color-coding the text data with the cell state values, and showing that some of them track quotes, brackets and other clearly identifiable aspects of the text.”