Initial Work on the Development of a Hardware-Based Gradient Descent Trained Expert System

Abstract

Prior work has introduced a form of explainable artificial intelligence that is able to precisely explain, in a human-understandable form, why it makes decisions. It is also able to learn to make better decisions without potentially learning illegal or invalid considerations. This defensible system is based on fractional value rule-fact expert systems and the use of gradient descent training to optimize rule weightings. This software system has demonstrated efficacy for many applications; however, it utilizes iterative processing and thus does not have a deterministic completion time. It also requires comparatively expensive general-purpose computing hardware to run on. This paper builds on prior work in the development of hardware-based expert systems and presents and assesses the efficacy of a hardware implementation of this system. It characterizes its performance and discusses its utility and trade-offs for several application domains.

Review and assessment of prior work on and future directions for gradient descent-trained expert systems

“…In [48], a hardware-based GDES (HGDES) implementation was introduced. This work built on prior work in developing hardware-based expert systems [49] and uses software training (using the GDES software that has been previously developed [50]) with hardware-based operations processing.…”

“…The current implementation, presented in [48], only performs processing using a hardware implementation (leaving training to the software system to perform). A hardware training implementation has been identified as a key area for potential future work.…”