Anytime Learning: A Step Toward Life-Long AI Machine Learning

  • Dr. James Crowder, CAES AT&E
  • Dr. Shelli Friess, LPC, NCC, ACS, School of Counseling, Walden University
  • Dr. John Carbone, Dept of Electrical and Computer Engineering, Southern Methodist University

Current machine learning architectures, strategies, and methods are typically static and non-interactive, making them incapable of adapting to changing and/or heterogeneous data environments, either in real-time, or in near-real-time. Typically, in real-time applications, large amounts of disparate data must be processed, learned from, and actionable intelligence provided in terms of recognition of evolving activities. Applications like Rapid Situational Awareness (RSA) used for support of critical systems (e.g., Battlefield Management and Control) require critical analytical assessment and decision support by automatically processing massive and increasingly amounts of data to provide recognition of evolving events, alerts, and providing actionable intelligence to operators and analysts [2 and 4]. Previous papers described strategies and algorithms for a continuously adapting, life-long machine learning systems. Here we present a step towards the creation of a continuous, life-long machine learning system with the introduction of the concept of an “Anytime Learning System” (ALS), in which learning can happen whenever data are available. Multiple concepts are presented, as the domain and environment(s) the system may encounter could determine the best approach for continuous learning. We feel this necessitates the notion of artificial feelings and emotions within a truly artificial cognitive system and would be helpful in defining when and what needs to be learned/processes at any point in time in the life of a continuously adapting/learning artificial intelligent system.

Full access to this whitepaper requires completing and submitting the following form: