Challenges in Machine Generation of Analytic Products from Multi-Source Data

The Intelligence Community Studies Board of the National Academies of Sciences, Engineering, and Medicine convened a workshop on August 9-10, 2017 to examine challenges in machine generation of analytic products from multi-source data. Workshop speakers and participants discussed research challenges related to machine-based methods for generating analytic products and for automating the evaluation of these products, with special attention to learning from small data, using multi-source data, adversarial learning, and understanding the human-machine relationship. This publication summarizes the presentations and discussions from the workshop.

Table of Contents

• Front Matter
• 1 Introduction
• 2 Session 1: Plenary
• 3 Session 2: Machine Learning from Image, Video, and Map Data
• 4 Session 3: Machine Learning from Natural Languages
• 5 Session 4: Learning from Multi-Source Data
• 6 Session 5: Learning from Noisy, Adversarial Inputs
• 7 Session 6: Learning from Social Media
• 8 Session 7: Humans and Machines Working Together with Big Data
• 9 Session 8: Use of Machine Learning for Privacy Ethics
• 10 Session 9: Evaluation of Machine-Generated Products
• 11 Session 10: Capability Technology Matrix
• Appendixes
• Appendix A: Biographical Sketches of Workshop Planning Committee
• Appendix B: Workshop Agenda
• Appendix C: Workshop Statement of Task
• Appendix D: Capability Technology Tables
• Appendix E: Acronyms
<