Daniel J. Clouse

2papers

2 Papers

RAJan 7, 2021
A Note on Rough Set Algebra and Core Regular Double Stone Algebras

Daniel J. Clouse

Rough Set Theory (RST), first introduced by Pawlak in 1982, is an approach for dealing with information systems where knowledge is uncertain or incomplete.\cite{Pawlak} It is of fundamental importance in many subfields of artificial intelligence and cognitive science.\cite{RSTppf} Given a universe $U$ with an equivalence relation $θ$, the pair $\langle U,θ\rangle$ is referred to as an information system and we denote its collection of rough sets $R_θ$. In our main Theorem we show $R_θ$ with $|θ_u| > 1\ \forall\ u \in U$ to be isomorphic to core regular double Stone algebras, CRDSA, that are complete and atomic, and that the crisp, or definable, sets form a complete atomistic Boolean algebra. These guarantees of infimum/supremeum for arbitrary subsets and formulations in terms of fundamental elements are likely useful if dealing with equivalence relations with an infinite number of partitions, such as projective Hilbert spaces. We further derive that every CRDSA is isomorphic to a subalgebra of a principal rough set algebra, $R_θ$, for some approximation space $\langle U,θ\rangle$. In our main Corollary we show explicitly how to embed $R_θ$ into the CRDSA and first demonstrate by extending the culminating finite example of \cite{RCRDSA}. As our capstone, we consider the projective Hilbert space of complex numbers, $\mathbb{C}$ and show, among other things, the power set of the set of pure states is a complete, atomistic Boolean algebra. In closing, we suggest other Quantum relevant applications that may be useful, such as Hilbert spaces of operators

LGSep 24, 2020
Advancing the Research and Development of Assured Artificial Intelligence and Machine Learning Capabilities

Tyler J. Shipp, Daniel J. Clouse, Michael J. De Lucia et al.

Artificial intelligence (AI) and machine learning (ML) have become increasingly vital in the development of novel defense and intelligence capabilities across all domains of warfare. An adversarial AI (A2I) and adversarial ML (AML) attack seeks to deceive and manipulate AI/ML models. It is imperative that AI/ML models can defend against these attacks. A2I/AML defenses will help provide the necessary assurance of these advanced capabilities that use AI/ML models. The A2I Working Group (A2IWG) seeks to advance the research and development of assured AI/ML capabilities via new A2I/AML defenses by fostering a collaborative environment across the U.S. Department of Defense and U.S. Intelligence Community. The A2IWG aims to identify specific challenges that it can help solve or address more directly, with initial focus on three topics: AI Trusted Robustness, AI System Security, and AI/ML Architecture Vulnerabilities.