DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction
arXiv:1909.09154 · doi:10.24963/ijcai.2020/319
Abstract
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 .
arXiv commentThis is published at IJCAI 2020
References in corpus (8)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
- Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI
- An Evaluation of the Human-Interpretability of Explanation
- Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
- Graying the black box: Understanding DQNs