Designing Optimal Knowledge Base for Neural Expert Systems

Abstract

One of the limitations of conventional expert systems and traditional machine induction methods in capturing human expertise is in their requirement of a large pool of structured samples from a multi-criteria decision problem domain. Then the experts may have difficulty in expressing explicitly the rules on how each decision was reached. To overcome these shortcomings, this paper reports on the design of an optimal knowledge base for machine induction with the integration of Artificial Neural Network (ANN) and Expert Systems (ES). In this framework, an orthogonal plan is used to define an optimal set of examples to be taken. Then holistic judgments of experts on these examples will provide a training set for an ANN to serve as an initial knowledge base for the integrated system. Any counter-examples in generalization over new cases will be added to the training set to retrain the network to enlarge its knowledge base.

The Effects of Absorptive Capacity, Intellectual Property and Innovation in SMEs

“…7, No. 4;2017 is significant at a level of 0.001; 2. It is very close to the acceptance threshold of 0.707; 3.…”

“…Some studies have confirmed the effectiveness of AC in complicated scenarios, for instance financial crises, to drive innovation and growth in SMEs (Liao, Welsch, & Stoica, 2003). Other researchers have reported that companies that take a collaborative approach to working with other companies achieve a higher development of human capital capacities by absorbing external knowledge and improving their innovation outlook (Camisón & Forés, 2010;Nguyen, 2017). Recently, the importance of AC has been explored in association with knowledge management and teamwork practices, which have allowed for the development of new products, the improvement of processes, and the increase in SME profitability (Leal-Rodríguez, Ariza-Montes, Roldán, & Leal-Millán, 2014;Spithoven et al, 2011).…”

“…7, No. 4;2017 are also based on historical costs, and therefore, may not accurately reflect the future (Kalyanaram, Robinson, & Urban, 1995). Managers' responses were employed to classify SME competitiveness based on profitability results using a five-point Likert scale (1=poor performance over past two years, 5=high performance over past two years).…”