Mitigating Fooling With Competitive Overcomplete Output Layer Neural Networks
Abstract
Although the introduction of deep learning has led to significant performance improvements in many machine learning applications, several recent studies have revealed that deep feedforward models are easily fooled. Fooling in effect results from overgeneralization of neural networks over regions far from the training data. To circumvent this problem this paper proposes a novel elaboration of standard neural network architectures called the competitive overcomplete output layer (COOL) neural network. Experiments demonstrate the effectiveness of COOL by visualizing the behavior of COOL networks in a low-dimensional artificial classification problem and by applying it to a high-dimensional vision domain (MNIST).
Publication Date
6-30-2017
Publication Title
Proceedings of the International Joint Conference on Neural Networks
Volume
2017-May
Number of Pages
518-525
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/IJCNN.2017.7965897
Copyright Status
Unknown
Socpus ID
85031044119 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85031044119
STARS Citation
Kardan, Navid and Stanley, Kenneth O., "Mitigating Fooling With Competitive Overcomplete Output Layer Neural Networks" (2017). Scopus Export 2015-2019. 7431.
https://stars.library.ucf.edu/scopus2015/7431