Representational Systems :: Communication Engineering Papers

Representational Systems This paper seeks to define a representational carcass in such a manner as to be competent of implementation in a connectionist, or neural, internet. A representational outline is defined and demonstrated to sustain the ability to produce outputs which achieve spheric minima. The paper concludes by showing that, while a feed-forward neural network is in open of representation, representation may be implemented in a recurrent, or internal feedback, connectionist network. Introduction Representational systems are commonly in the Artificial Intelligence (AI) domain of symbolic logical system. Expert Systems are programmed into estimator systems by recording the step-by-step ratiocinative methodology of experts to minimize the be or maximize the utility of their decisions. Logical statements, or beliefs, be they hairy or hard, are established as rules. Anothe r branch of AI, Connectionism, attempts to gird systems, often in artificial neural networks (ANNs), that implement the methodologies of the illogical, inexplicable, or splanchnic capabilities of distributed systems such as pattern recognition systems. Here, it is not some logical mapping of input to output, but rather a holistic multitude of inputs which indicate micro-features which may or may not synergistically produce a desired output. While connectionist systems are recognized as being capable of distributed, non-representational processing, they may also possess the capability to additionally perform the rule-based logic of representational systems. As will be shown, not all connectionist networks possess the appropriate architecture for this task. Thus, a neural network, depending upon its architecture, may possess the