Kirstie L. Bellman, "The Modelling Issues Inherent in Test- ing and Evaluating Knowledge-based Syst eros", pp. 199- 215 in Chris Culbert (ed.), Special Issue: Verification and Val- idation of Knowledge Based Systems, Expert Systems With Applications Journal, Volume 1, No. 3 (1990)  Home/Search   Document Not in Database   Summary   Related Articles   Check

....Copernicus for many years after both existed. In our view, models with more explanatory power are much more likely to be predictively useful than ones that merely fit . Our approach to validation of internal consistencies in complex systems leads to many other verification and validation methods [1] [6] as well as other kinds of exploratory data analysis. Of course, there is no guarantee that any exploratory data analysis method reflects any actual physical process; that has to be checked or explained separately. On the other hand, many unexpected properties cannot be found if one makes too ....

Kirstie L. Bellman, "The Modelling Issues Inherent in Testing and Evaluating Knowledge-based Systems ", pp. 199-215 in Chris Culbert (ed.), Special Issue: Verification and Validation of Knowledge Based Systems, Expert Systems With Applications Journal, Volume 1, No. 3 (1990)

....with real world phenomena on perhaps several different time scales. This culture has built systems like this in the past, relying on what we have called heroic engineering . Over the last decade, we have built systems that supply more useful com pater support to the design process [6] 17] [3] [18] tt] 7] 38] We are now trying to put some more science to it since the heroes are few and far between, and the systems that this culture is trying to build are continuing to get larger and more complex. Our work on autonomous systems [4] 5] 9] is based on the notion from theoretical ....

....problem, and we claim that considering the commonalities between them points towards a solution. The problem with each approach separately, as we see it, and in our opinion the reason it has not worked well in practice, is that there is no such thing as generic knowledge or a generic model [3]. All knowledge is situated, in a context, for a purpose, or according to a viewpoint [23] 44] 2] 4] Therefore, any mechanism that does not take into account the context and viewpoint cannot succeed except in the small scale. Combining the two methods by itself suffers from the same problem. ....

[Article contains additional citation context not shown here]

Kirstie L. Bellman, "The Modelling Issues Inherent in Test- ing and Evaluating Knowledge-based Syst eros", pp. 199- 215 in Chris Culbert (ed.), Special Issue: Verification and Val- idation of Knowledge Based Systems, Expert Systems With Applications Journal, Volume 1, No. 3 (1990)

....processes as agents, the computational resources as tools, and the meta knowledge as guides to the tools. The result is a computationally reflective multi agent architecture that we think is very interesting as an approach to constructing complex systems. 1 Introduction Over the last decade or so [7] [39] we have developed a computationally reflective, knowledge based approach to integration infrastructure, called wrappings . We were originally driven by our recognition that the development of space systems (with their tens of millions of lines of code, written by hundreds of organizations ....

....the declarative ideal of not having to specify a solution method can be terrifically liberating in conceptual clarity. 3 However, not being able to specify a solution method can be a terrible limitation when a good one is known. Since it is one of our underlying philosophical principles [16] [7] [82] that NO one method suffices for all problems, we would rather be able to use an alternative method when we know a good one, and we would rather not have to program it in a backtracking style, or indeed according to any style chosen a priori, since the difficulty of fitting the method to that ....

[Article contains additional citation context not shown here]

Kirstie L. Bellman, "The Modelling Issues Inherent in Testing and Evaluating Knowledge-based Systems ", pp. 199-215 in Chris Culbert (ed.), Special Issue: Verification and Validation of Knowledge Based Systems, Expert Systems With Applications Journal, Volume 1, No. 3 (1990)

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC