daniel wilson and ben conklin
play

DANIEL WILSON AND BEN CONKLIN Integrating AI with Foundation - PowerPoint PPT Presentation

DANIEL WILSON AND BEN CONKLIN Integrating AI with Foundation Intelligence for Actionable Intelligence INTEGRATING AI WITH FOUNDATION INTELLIGENCE FOR ACTIONABLE INTELLIGENCE in an arms race for artificial intelligence - Dr. Anthony


  1. DANIEL WILSON AND BEN CONKLIN Integrating AI with Foundation Intelligence for Actionable Intelligence

  2. INTEGRATING AI WITH FOUNDATION INTELLIGENCE FOR ACTIONABLE INTELLIGENCE

  3. “…in an arms race for artificial intelligence” - Dr. Anthony Vinci, NGA

  4. MICROSOFT IBM AMAZON GOOGLE SAP Azure ML Watson ML Service Amazon ML Cloud AI Leonardo Cognitive Services DSX Cloud ML (TF) SAP Analytics Cloud Cloud ML Azure Bot Service Cognitive Computing ML Server SPSS Leonardo ML for z/OS SAP Predictive Analytics On-premise ML -- -- Office 365 Predictive Maintenance Demand Forecasting, Search, Ads, Gmail, Fraud Mgmt, SAPHIRE, PowerPoint Targeted Marketing Recommendations, Translation, YouTube, S/4HANA, Fieldglass, Enhanced Products Outlook .. Search, Merchandising Maps.. Total Workforce Insight .. Placement, Fraud.. New Products Cortana Assistant -- Alexa, Prime Air Delivery Google Assistant -- Drones, Grocery Stores

  5. CNTK Object Tracking Object Detection Caffe Artificial Intelligence Theano scikit-learn Computer Vision Random Forest Neural Networks Machine Learning Natural Language Cognitive Processing Computing TensorFlow T-SNE Deep Keras GeoAI Learning Support Vector Machines Dimensionality Reduction

  6. 1950’s 1960’s Artificial Intelligence 1970’s Machine 1980’s Learning 1990’s 2000’s Deep 2010’s Learning

  7. Artificial Intelligence Video game Natural behavioral AI Language Processing Computer Machine Vision Robotics Learning Keras Theano TensorFlow CNTK IBM scikit-learn Watson Deep Learning Convolutional Neural Networks

  8. Applications of Machine Learning Cyber Intrusion Detection eCommerce Spam Filtering Fraud Detection Transportation Management Facial Recognition

  9. Why Now? 1. More Data 2. More Compute 3. Better Algorithms

  10. ML Value Prediction Anomaly Detection Automation Root-cause Identification

  11. GIS users have been doing machine learning Classification Prediction GIS Clustering

  12. Integration of Machine Learning and Deep Learning with GIS GIS

  13. Deep Learning Amazing Rate of Improvement Image Recognition Pedestrian Detection Object Detection IMAGENET CALTECH KITTI Convolutional Neural Networks (CNNs)

  14. Real-Time Land Cover Classification Microsoft Cognitive Toolkit

  15. Use Artificial Intelligence to find system faults Predictive Maintenance IBM Watson

  16. Real-Time Object Recognition from Video TensorFlow

  17. GIS and Natural Language Processing Integration

  18. “This is not either human analysis or artificial intelligence , it's got to be some combination of the two .” Adm. Mike Rogers, Director, National Security Agency & Commander of U.S. Cyber Command

  19. Technology Drivers for Advanced Analytics 1. More Data 2. More Compute 3. Better Algorithms

  20. Categories of Machine Learning in GIS Classification Prediction GIS Clustering

  21. Machine Learning Tools in GIS Classification Prediction • Empirical Bayesian • Maximum Likelihood Kriging Classification • Areal Interpolation • Random Trees • EBK Regression • Support Vector Machine Prediction • Ordinary Least Squares Clustering Regression and Exploratory Regression • Spatially Constrained • Geographically Weighted Multivariate Clustering Regression • Multivariate Clustering • Density-based Clustering • Image Segmentation • Hot Spot Analysis • Cluster and Outlier Analysis • Space Time Pattern Mining

  22. Prediction Using ng the known wn to esti tima mate te the unknow nown Use Case: Accurately predict impacts of climate change on local temperature using global climate model data In ArcGIS : Empirical Bayesian Kriging, Areal Interpolation, EBK Regression Prediction, Ordinary Least Squares Regression and Exploratory Regression, Geographically Weighted Regression

  23. Clustering The groupi uping ng of obser serva vatio ions ns based ed on simil ilarities ities of values es or locat catio ions ns Use Case: Given the nearly 50,000 reports of traffic between 5pm and 6pm in Los Angeles (from Traffic Alerts by Waze), where are traffic zones that can be used to elicit feedback from current drivers in the area? In ArcGIS : Spatially Constrained Multivariate Clustering, Multivariate Clustering, Density-based Clustering, Image Segmentation, Hot Spot Analysis, Cluster and Outlier Analysis, Space Time Pattern Mining

  24. Classification The process cess of decid cidin ing g to which h catego egory y an objec ect shoul uld d be assigne gned d based d on a traini ning ng dataset set Use Case: Classify impervious surfaces to help effectively prepare for storm and flood events based on the latest high-resolution imagery In ArcGIS : Maximum Likelihood Classification, Random Trees, Support Vector Machine

  25. Integration of Machine Learning and Deep Learning with GIS GIS

  26. Demo: Transfer Learning

  27. Enterprise Approach to Machine Learning Leveraging Geography for Improved Understanding Analyst Tools Visualization and Data Conditioning and Exploration Modeling Management Raster Real-Time Vector Distributed Analytics

  28. Data Conditioning Extract, Transform, Enrich, Georeference, Validate Making Data Ready for Analysis And Use in Apps Point Clouds Imagery Unstructured Text Data Lakes Sensor Feeds Vector Foundation Data

  29. Visualization and Exploration Exploratory Data Analysis Visualization

  30. Modeling and Spatial Analytics Develop and Capture new tradecraft Spatio-Temporal Data Science Modeling Analytic Services Python Machine Learning & Artificial Intelligence

  31. Real-Time Analytics Workflow Analysis Alerting Situational Awareness Visualization Contextualization Collection Real-Time Analytics • GeoFencing • Aggregation • Detection • Filter Big Data Archive

  32. Raster Analytics Workflow Feature Change Extraction Detection Visualization Dynamic Image Collection Processing • Ortho-on-the-fly • Classification • Feature Extraction • Mosaicking

  33. Vector Analytics Workflow Classification, Clustering, Prediction Pattern- Predictive of-Life Analytics Trend Analysis Link Analysis Big Data Analytics Big Data Archive • Space-Time • Hot Spots • Density • Proximity

  34. Demo: Event Prediction

  35. Applying to Intelligence Problems Locations and Targets Known Behaviors and Signatures Research Search Unknown Known Monitor Discover Unknown

  36. The Intelligence Cycle Requirements Dissemination Tasking Traditional Emphasis Modern Emphasis Exploitation Collection Processing

  37. Leveraging Foundation Intelligence Observations Social Data Landscape Data Cultural Data

  38. Actionable Intelligence Observe OODA loop Speed is the key Act Orient Speed is relative Decide

  39. 100% Intelligence Certainty X Data 0% 0 Time & Resources

  40. Reduce Time to Action 100% Intelligence Certainty X Data 0% 0 Time & Resources

  41. Implementing Analytic Platform Impacts on Entire Organization Plan for Prepare Infrastructure Evolving Structure Focus on Collaborate with Enhance Analyst Verification and Industry Tradecraft Validation

Recommend


More recommend