Explainable Forecasts of Disruptive Events using Recurrent Neural Networks

被引：2
|
作者：
Buczak, Anna L. [1 ]
Baugher, Benjamin D. [1 ]
Berlier, Adam J. [1 ]
Scharfstein, Kayla E. [1 ,2 ]
Martin, Christine S. [1 ]
机构：
[1] Johns Hopkins Univ, Appl Phys Lab, Laurel, MD 20723 USA
[2] Carnegie Mellon Univ, Laurel, MD USA
来源：
2022 IEEE INTERNATIONAL CONFERENCE ON ASSURED AUTONOMY (ICAA 2022) | 2022年
关键词：
resilient; explainable deep learning; interpretable machine learning; acceptance of machine learning models; AI safety; disruptive event; forecasting; LSTM; RNN; SHAP; ENSEMBLE;
D O I：
10.1109/ICAA52185.2022.00017
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
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.
引用
收藏
页码：64 / 73
页数：10
相关论文
共 50 条
  • [21] DIRECTION FINDING USING CONVOLUTIONAL NEURAL NETWORKS and CONVOLUTIONAL RECURRENT NEURAL NETWORKS
    Uckun, Fehmi Ayberk
    Ozer, Hakan
    Nurbas, Ekin
    Onat, Emrah
    2020 28TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2020,
  • [22] Rainfall Prediction using Spatial Convolutional Neural Networks and Recurrent Neural Networks
    Lestari, Nadia Dwi Puji
    Djamal, Esmeralda Contessa
    2022 International Conference on Data Science and Its Applications, ICoDSA 2022, 2022, : 12 - 17
  • [23] Explainable neural networks that simulate reasoning
    Paul J. Blazek
    Milo M. Lin
    Nature Computational Science, 2021, 1 : 607 - 618
  • [24] The Road to Explainable Graph Neural Networks
    Ranu, Sayan
    SIGMOD RECORD, 2024, 53 (03)
  • [25] Prediction Model Using Recurrent Neural Networks
    Jahan, Israt
    Sajal, Sayeed Z.
    Nygard, Kendall E.
    2019 IEEE INTERNATIONAL CONFERENCE ON ELECTRO INFORMATION TECHNOLOGY (EIT), 2019, : 390 - 395
  • [26] Speech prediction using recurrent neural networks
    Varoglu, E
    Hacioglu, K
    ELECTRONICS LETTERS, 1999, 35 (16) : 1353 - 1355
  • [27] Explainable neural networks that simulate reasoning
    Blazek, Paul J.
    Lin, Milo M.
    NATURE COMPUTATIONAL SCIENCE, 2021, 1 (09): : 607 - 618
  • [28] Authorship Identification using Recurrent Neural Networks
    Gupta, Shriya T. P.
    Sahoo, Jajati Keshari
    Roul, Rajendra Kumar
    PROCEEDINGS OF 3RD INTERNATIONAL CONFERENCE ON INFORMATION SYSTEM AND DATA MINING (ICISDM 2019), 2019, : 133 - 137
  • [29] Scoring Summaries Using Recurrent Neural Networks
    Ruseti, Stefan
    Dascalu, Mihai
    Johnson, Amy M.
    McNamara, Danielle S.
    Balyan, Renu
    McCarthy, Kathryn S.
    Trausan-Matu, Stefan
    INTELLIGENT TUTORING SYSTEMS, ITS 2018, 2018, 10858 : 191 - 201
  • [30] Network restoration using recurrent neural networks
    Sri Venkateswara Univ, Bangalore, India
    Int J Network Manage, 5 (264-273):
12345