Understanding Machine Intelligence (UMI)
Abstract
The Understanding Machine Intelligence (UMI) program will develop techniques that enable artificial intelligence (AI) systems to better support users through transparent operation. In the future, the U.S. military will encounter adversary systems that are AI-enabled. Maintaining "AI-superiority" will require AI-enabled systems capable of performing increasingly complex functions with high degrees of reliability and safety. Significantly, in order for developers and users to feel confident enough to deploy and use AI-enabled systems, these systems must operate with a high degree of transparency. UMI will develop AI technologies that support transparency by providing supporting rationale and logic sequences to clarify the basis for and reliability of outputs. In addition, efforts will be made to develop a mathematically rigorous virtual stability theory for AI-enabled systems analogous to the (conventional) stability theory developed for dynamical systems (solutions to systems of differential equations). Such a virtual stability theory will enable the creation of feedback mechanisms that flag and interrupt anomalous outputs and behaviors. UMI implementations will be developed and demonstrated in next-generation systems.
Document Details
- Document Type
- Accomplishment
- Publication Date
- Oct 01, 2016
- Source ID
- f7064a651ecb97588c7895c0ac79c01d
Related Documents
- Root: TACTICAL TECHNOLOGY