Fetching the paper…

Reading the bibliography…

2016

Interpretation of Prediction Models Using the Input Gradient

Hechtlinger, Yotam

Original
PDF
Post on X

Understand

State of the art machine learning algorithms are highly optimized to provide the optimal prediction possible, naturally resulting in complex models.

While these models often outperform simpler more interpretable models by order of magnitudes, in terms of understanding the way the model functions, we are often facing a "black box".
In this paper we suggest a simple method to interpret the behavior of any predictive model, both for regression and classification.
Given a particular model, the information required to interpret it can be obtained by studying the partial derivatives of the model with respect to the input.

Interpretation of Prediction Models Using the Input Gradient · Around

Built on

Natural language processing (almost) from scratch
Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa · 2011
Earlier work this paper cites.
Learning word vectors for sentiment analysis
Andrew L Maas, Raymond E Daly, Peter T Pham, Dan Huang, Andrew Y Ng, and Christopher Potts · 2011
Earlier work this paper cites.
Convolutional neural networks for sentence classification
Original
Yoon Kim · 2014
Earlier work this paper cites.

Similar

Keras, https://github.com/fchollet/keras, 2015
François Chollet · 2015
Cited alongside, same era.
Deepdream, https://github.com/google/deepdream, 2015
Alexander Mordvintsev, Christopher Olah, and Mike Tyka · 2015
Cited alongside, same era.
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich · 2015
Cited alongside, same era.

Then

Supervised and semi-supervised text categorization using one-hot lstm for region embeddings
Original
Rie Johnson and Tong Zhang · 2016
Closest in time.
" why should i trust you?": Explaining the predictions of any classifier
Original
Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin · 2016
Closest in time.
Theano: A Python framework for fast computation of mathematical expressions
Original
Theano Development Team · 2016
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…