Abstract
Deep Taylor Decomposition is a method used to explain neural network decisions.
When applying this method to non-dominant classifications, the resulting explanation does not reflect important features for the chosen classification. We propose that this is caused by the dense layers and propose a method to alleviate the effect by applying regularization. We assess the result by measuring the quality of the resulting explanations objectively and subjectively.
When applying this method to non-dominant classifications, the resulting explanation does not reflect important features for the chosen classification. We propose that this is caused by the dense layers and propose a method to alleviate the effect by applying regularization. We assess the result by measuring the quality of the resulting explanations objectively and subjectively.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017) |
| Number of pages | 8 |
| Publication date | 2017 |
| Publication status | Published - 2017 |
| Event | 31st Conference on Neural Information Processing Systems - Long Beach, United States Duration: 4 Dec 2017 → 9 Dec 2017 |
Conference
| Conference | 31st Conference on Neural Information Processing Systems |
|---|---|
| Country/Territory | United States |
| City | Long Beach |
| Period | 04/12/2017 → 09/12/2017 |