Artificial Neural Diagnostics and Prognostics:
Self-Soothing in Cognitive Systems

  • Dr. James Crowder, Colorado Engineering Inc.
  • John N. Carbone, Electrical and Computer Engineering Dept., Southern Methodist University

Self-diagnostics and prognostics in multi-agent processing systems is explored in the context of self-soothing concepts in Neuropsychology. This is one of the first steps to facilitate Systems-Level Thinking in AI. Autonomous or semiautonomous system must be able to understand, at a systemwide level, how every part of the system is influencing the other parts of the system. This drives the need for complete selfassessment within the AI system. The use of emotional memory and autonomic nervous state recall can be used to provide contextual cognition for system-level diagnostic and prognostics in large-scale systems. The use of an Artificial Cognitive Neural Framework with intelligent information software agents can be utilized to emulate emotional learning to facilitate selfsoothing, which equates to self healing in artificial neural systems. This paper describes the architecture and specifications of software agents that are used to provide selfsoothing and self-healing constructs for intelligent systems.

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