TY - JOUR
T1 - INNvestigate neural networks!
AU - Alber, Maximilian
AU - Lapuschkin, Sebastian
AU - Seegerer, Philipp
AU - Hägele, Miriam
AU - Schütt, Kristof T.
AU - Montavon, Grégoire
AU - Samek, Wojciech
AU - Müller, Klaus Robert
AU - Dähne, Sven
AU - Kindermans, Pieter Jan
N1 - Funding Information:
Correspondence to MA, SL, KRM, WS and PJK. This work was supported by the Federal Ministry of Education and Research (BMBF) for the Berlin Big Data Center BBDC (01IS14013A). Additional support was provided by the BK21 program funded by Korean National Research Foundation grant (No. 2012-005741) and the Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (no. 2017-0-00451, No. 2017-0-01779).
Publisher Copyright:
© 2019 Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer, Miriam Hägele, Kristof T. Schütt, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller, Sven Dähne, Pieter-Jan Kindermans.
PY - 2019/5/1
Y1 - 2019/5/1
N2 - In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. Therefore, it is crucial that domain specialists can understand and analyze actions and predictions, even of the most complex neural network architectures. Despite these arguments neural networks are often treated as black boxes. In the attempt to alleviate this shortcoming many analysis methods were proposed, yet the lack of reference implementations often makes a systematic comparison between the methods a major effort. The presented library iNNvestigate addresses this by providing a common interface and out-of-thebox implementation for many analysis methods, including the reference implementation for PatternNet and PatternAttribution as well as for LRP-methods. To demonstrate the versatility of iNNvestigate, we provide an analysis of image classifications for variety of state-of-the-art neural network architectures.
AB - In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. Therefore, it is crucial that domain specialists can understand and analyze actions and predictions, even of the most complex neural network architectures. Despite these arguments neural networks are often treated as black boxes. In the attempt to alleviate this shortcoming many analysis methods were proposed, yet the lack of reference implementations often makes a systematic comparison between the methods a major effort. The presented library iNNvestigate addresses this by providing a common interface and out-of-thebox implementation for many analysis methods, including the reference implementation for PatternNet and PatternAttribution as well as for LRP-methods. To demonstrate the versatility of iNNvestigate, we provide an analysis of image classifications for variety of state-of-the-art neural network architectures.
KW - Analyzing classifiers
KW - Artificial neural networks
KW - Computer vision
KW - Deep learning
KW - Explaining classifiers
UR - http://www.scopus.com/inward/record.url?scp=85072598988&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:85072598988
VL - 20
JO - Journal of Machine Learning Research
JF - Journal of Machine Learning Research
SN - 1532-4435
ER -