Network Dissection


Institutions :
MIT
Authors :
David Bau, Bolei Zhou, Aditya Khosla, Aude Oliva, Antonio Torralba
Publication :
Network Dissection: Quantifying Interpretability of Deep Visual Representations
Source Code :
https://github.com/CSAILVision/NetDissect
Further Info :
http://netdissect.csail.mit.edu/co


PatternNet and PatternAttribution


Institutions :
Google Brain, TU Berlin
Authors :
Pieter-Jan Kindermans, Kristof T. Schutt & Maximilian Alber, K-R. Müller, Dumitru Erhan & Been Kim, Sven Dahne
Publication :
LEARNING HOW TO EXPLAIN NEURAL NETWORKS: PATTERNNET AND PATTERNATTRIBUTION
Source Code :
https://openreview.net/pdf?id=Hkn7CBaTW


The LRP Toolbox for Artificial Neural Networks


Institutions :
Fraunhofer, Berlin Institute of Tech., Korea
Authors :
S. Lapuschkin, A. Binder, G. Montavon, K-R. Müller, W. Samek
Publication :
The LRP Toolbox for Artificial Neural Networks, JMLR, 2016
Source Code :
https://github.com/VigneshSrinivasan10/interprettensor


Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car


Institutions :
NVIDIA, New York University, Google
Authors :
B. Mariusz et. al.
Publication :
Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
Source Code :
https://github.com/maxritter/SDC-End-to-end-driving