Learning and Reasoning in Complex Coalition Information Environments: A Critical Analysis

In this paper we provide a critical analysis with metrics that will inform guidelines for designing distributed systems for Collective Situational Understanding (CSU). CSU requires both collective insight-i.e., accurate and deep understanding of a situation derived from uncertain and often sparse data and collective foresight-i.e., the ability to predict what will happen in the future. When it comes to complex scenarios, the need for a distributed CSU naturally emerges, as a single monolithic approach not only is unfeasible: it is also undesirable. We therefore propose a principled, critical analysis of AI techniques that can support specific tasks for CSU to derive guidelines for designing distributed systems for CSU.

[1]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[2]  Hava T. Siegelmann,et al.  On the Computational Power of Neural Nets , 1995, J. Comput. Syst. Sci..

[3]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[4]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[5]  Matthew Richardson,et al.  Markov logic networks , 2006, Machine Learning.

[6]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[7]  Mary Missy Cummings,et al.  Man versus Machine or Man + Machine? , 2014, IEEE Intelligent Systems.

[8]  Luc De Raedt,et al.  Inducing Probabilistic Relational Rules from Probabilistic Examples , 2015, IJCAI.

[9]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Alun D. Preece,et al.  Cognitive computing for coalition situational understanding , 2017, 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI).

[11]  Taisuke Sato,et al.  A Statistical Learning Method for Logic Programs with Distribution Semantics , 1995, ICLP.

[12]  Nathalie Weizmann,et al.  Autonomous weapon systems under international law , 2014 .

[13]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Lance M. Kaplan,et al.  Efficient belief propagation in second-order Bayesian networks for singly-connected graphs , 2017, Int. J. Approx. Reason..

[15]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[17]  Alun D. Preece,et al.  Deep learning for situational understanding , 2017, 2017 20th International Conference on Information Fusion (Fusion).

[18]  Thomas G. Dietterich.  Steps Toward Robust Artificial Intelligence , 2017, AI Mag..

[19]  Takuya Akiba,et al.  Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes , 2017, ArXiv.

[20]  Murat Sensoy,et al.  Human-in-the-loop situational understanding via subjective Bayesian networks , 2017 .

[21]  Hai Zhuge,et al.  Automatic Maintenance of the Category Hierarchy , 2013, 2013 Ninth International Conference on Semantics, Knowledge and Grids.

[22]  Eric P. Xing,et al.  Harnessing Deep Neural Networks with Logic Rules , 2016, ACL.

[23]  Luc De Raedt,et al.  ProbLog: A Probabilistic Prolog and its Application in Link Discovery , 2007, IJCAI.

[24]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[25]  Kjølv Egeland.  Lethal Autonomous Weapon Systems under International Humanitarian Law , 2016 .

[26]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[27]  Kathryn B. Laskey,et al.  Multi-entity Bayesian networks for situation assessment , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[28]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[29]  Luc De Raedt,et al.  Probabilistic (logic) programming concepts , 2015, Machine Learning.

[30]  Frank A. Pasquale,et al.  [89WashLRev0001] The Scored Society: Due Process for Automated Predictions , 2014 .

[31]  Michael I. Jordan,et al.  Graphical Models, Exponential Families, and Variational Inference , 2008, Found. Trends Mach. Learn..

[32]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[33]  Sergio Guadarrama,et al.  Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Luc De Raedt,et al.  Inference and learning in probabilistic logic programs using weighted Boolean formulas , 2013, Theory and Practice of Logic Programming.

[35]  Nate Silver,et al.  The signal and the noise : why so many predictions fail but some don't , 2012 .

[36]  Christopher D. Wickens,et al.  Stages and Levels of Automation: An Integrated Meta-analysis , 2010 .