DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction

Schulz A, Hinder F, Hammer B (2020)
In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}.

Konferenzbeitrag | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Abstract / Bemerkung
Machine learning algorithms using deep architectures have been able to implement increasingly powerful and successful models. However, they also become increasingly more complex, more difficult to comprehend and easier to fool. So far, most methods in the literature investigate the decision of the model for a single given input datum. In this paper, we propose to visualize a part of the decision function of a deep neural network together with a part of the data set in two dimensions with discriminative dimensionality reduction. This enables us to inspect how different properties of the data are treated by the model, such as outliers, adversaries or poisoned data. Further, the presented approach is complementary to the mentioned interpretation methods from the literature and hence might be even more useful in combination with those. Code is available at https://github.com/LucaHermes/DeepView
Erscheinungsjahr
2020
Titel des Konferenzbandes
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}
Konferenz
International Joint Conferences on Artificial Intelligence
Konferenzort
Yokohama, Japan
Konferenzdatum
2020-07-11 – 2020-07-17
Page URI
https://pub.uni-bielefeld.de/record/2943260

Zitieren

Schulz A, Hinder F, Hammer B. DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}. 2020.
Schulz, A., Hinder, F., & Hammer, B. (2020). DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}. https://doi.org/10.24963/ijcai.2020/319
Schulz, Alexander, Hinder, Fabian, and Hammer, Barbara. 2020. “DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction”. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}.
Schulz, A., Hinder, F., and Hammer, B. (2020). “DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction” in Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}.
Schulz, A., Hinder, F., & Hammer, B., 2020. DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}.
A. Schulz, F. Hinder, and B. Hammer, “DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction”, Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}, 2020.
Schulz, A., Hinder, F., Hammer, B.: DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}. (2020).
Schulz, Alexander, Hinder, Fabian, and Hammer, Barbara. “DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction”. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI-20}. 2020.

Link(s) zu Volltext(en)
Access Level
OA Open Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Quellen

arXiv: 1909.09154

Suchen in

Google Scholar