Journal
2022 IEEE INTERNATIONAL CONFERENCE ON ASSURED AUTONOMY (ICAA 2022)
Volume -, Issue -, Pages 64-73Publisher
IEEE COMPUTER SOC
DOI: 10.1109/ICAA52185.2022.00017
Keywords
resilient; explainable deep learning; interpretable machine learning; acceptance of machine learning models; AI safety; disruptive event; forecasting; LSTM; RNN; SHAP
Ask authors/readers for more resources
This paper presents the Crystal Cube method for forecasting disruptive events worldwide, focusing on Irregular Leadership Change. The method utilizes a Recurrent Neural Network with Long-Short Term Memory units and emphasizes the explanation of network forecasts. SHapley Additive exPlanations is used for individual forecast explanations, and the method can be extended to Deep Reinforcement Learning models for self-driving cars or unmanned fighter jets.
This paper describes the Crystal Cube method we developed for forecasting disruptive events around the world, specifically Irregular Leadership Change. Crystal Cube uses a Recurrent Neural Network (RNN) with Long-Short Term Memory (LSTM) units for forecasting. In this paper special emphasis is put on explanations of the network forecasts. We are using SHapley Additive exPlanations (SHAP) for individual forecast explanations and we are aggregating the explanations separately for True Positives, False Positives, True Negatives, and False Negatives. The method can be extended to Deep Reinforcement Learning models for self-driving cars or unmanned fighter jets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available