This paper introduces a new approach to designing smart control chips that enables automatic synthesis of real-time control systems from agent specifications. An agent specification is compiled into a hardware description format, such as RTL-VHDL (Register Transfer Level-VLSI Hardware Description Language) or RTL Verilog, which is synthesized using computer-assisted tools to develop ASIC masks or FPGA configurations. A rule-based specification language called Layered Argumentation System (LAS) is defined and a sound and complete mapping to Verilog is developed. LAS combines fuzzy reasoning and nonmonotonic reasoning. This enables chip designers to capture commonsense knowledge and concepts having varying degrees of confidence collaboratively and incrementally.

This work presents a new class of neural network models constrained by biological levels of sparsity and weight-precision, and employing only local weight updates. Concept learning is accomplished through the rapid recruitment of existing network knowledge - complex knowledge being realised as a combination of existing basis concepts. Prior network knowledge is here obtained through the random generation of feedforward networks, with the resulting concept library tailored through distributional bias to suit a particular target class. Learning is exclusively local - through supervised Hebbian and Winnow updates - avoiding the necessity for backpropagation of error and allowing remarkably rapid learning. The approach is demonstrated upon concepts of varying difficulty, culminating in the well-known Monks and LED benchmark problems.

To date, the preponderance of techniques for eliciting the knowledge embedded in trained artificial neural networks (ANN's) has focused primarily on extracting rule-based explanations from feedforward ANN's. The ADT taxonomy for categorizing such techniques was proposed in 1995 to provide a basis for the systematic comparison of the different approaches. This paper shows that not only is this taxonomy applicable to a cross section of current techniques for extracting rules from trained feedforward ANN's but also how the taxonomy can be adapted and extended to embrace a broader range of ANN types (e.g., recurrent neural networks) and explanation structures. In addition the paper identifies some of the key research questions in extracting the knowledge embedded within ANN's including the need for the formulation of a consistent theoretical basis for what has been, until recently, a disparate collection of empirical results.