Corpus ID: 225103021

Investigating the Robustness of Artificial Intelligent Algorithms with Mixture Experiments

@article{Lian2020InvestigatingTR,
  title={Investigating the Robustness of Artificial Intelligent Algorithms with Mixture Experiments},
  author={Jiayi Lian and Laura Freeman and Y. Hong and Xinwei Deng},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.15551}
}
Artificial intelligent (AI) algorithms, such as deep learning and XGboost, are used in numerous applications including computer vision, autonomous driving, and medical diagnostics. The robustness of these AI algorithms is of great interest as inaccurate prediction could result in safety concerns and limit the adoption of AI systems. In this paper, we propose a framework based on design of experiments to systematically investigate the robustness of AI classification algorithms. A robust… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 49 REFERENCES
Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis.
  • 45
Concrete Problems in AI Safety
  • 867
  • PDF
AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation
  • 357
  • PDF
Intriguing properties of neural networks
  • 6,436
  • PDF
Evaluating Robustness of Neural Networks with Mixed Integer Programming
  • 246
  • PDF
CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
  • 48
  • PDF
A Unified Approach to Interpreting Model Predictions
  • 2,393
  • PDF
DeepTest: Automated Testing of Deep-Neural-Network-Driven Autonomous Cars
  • 516
  • PDF
Steps Toward Robust Artificial Intelligence
  • 54
Verifying Neural Networks with Mixed Integer Programming
  • 92
  • PDF
...
1
2
3
4
5
...