Argo: An Analogical Reasoning System for Solving Design Problems

Huhns, Michael N.; Acosta, R.D.

doi:10.1016/b978-0-12-660562-4.50010-8

Cited by 23 publications

(16 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AI design paradigm may be combined with other design paradigms to establish a "grand" problem solving strategy for the designer or design system. It is only very recently that the use of past cases is beginning to be recognized in the design automation literature [76], [32], [47]. The process of casebased design consists of the following steps that are iteratively applied as new subgoals are generated during problem-solving [115]: 1) development of a functional description through the use of qualitative relations explaining how the inputs and outputs are related; 2) retrieval of cases which results with a set of design cases (or case parts) bearing similarity to a given collection of features; 3) development of a synthesis strategy which describes how the various cases and case pieces will fit together to yield a working design; 4) realization of the synthesis strategy at the physical level; 5) verification of the design against the desired specifications through quantitative and qualitative simulation; and 6) debugging which involves the process of asking relevant questions and modifying them based on a causal explanation of the bug.…”

Section: G the Ai Design Paradigmmentioning

confidence: 99%

The design process: properties, paradigms, and structure

Braha

Maimon

1997

IEEE Trans. Syst., Man, Cybern. A

104

View full text Add to dashboard Cite

In this paper, we examine the logic and methodology of engineering design from the perspective of the philosophy of science. The fundamental characteristics of design problems and design processes are discussed and analyzed. These characteristics establish the framework within which different design paradigms are examined. Following the discussions on descriptive properties of design, and the prescriptive role of design paradigms, we advocate the plausible hypothesis that there is a direct resemblance between the structure of design processes and the problem solving of scientific communities. The scientific community metaphor has been useful in guiding the development of general purpose highly effective design process meta-tools [73], [125]. His research within engineering design focuses on developing methods to help the designer move from the conceptual phase to the realization of the physical device. To achieve this objective, he has developed the formal general design theory (FGDT), which is a mathematical theory of design. He has developed methods to solve routine design with group technology, genetic algorithms, and simulated annealing, to define computerized architecture, structure, and databases for the conceptual design process, and to develop a framework of logic decomposition and case-based reasoning methodology for mechanical design. He is also co-authoring, with O. Maimon, a book on the foundations of engineering design. Additional interests include real-time scheduling of flexible manufacturing systems, inventory management, risk and decision analyses, and group technology. His papers have been published in several journals, including the IEEE

show abstract

Section: G the Ai Design Paradigmmentioning

confidence: 99%

The design process: properties, paradigms, and structure

Braha

Maimon

1997

IEEE Trans. Syst., Man, Cybern. A

104

View full text Add to dashboard Cite

show abstract

“…Current GA-based machine learning systems (classifier systems) use rules to store past experience to improve their performance over time [1][2][3][4][5]. However, many application areas, especially in the design domain, are more suited to a case-based storage of past experience [6][7][8][9]. This paper proposes and describes a system that uses a case-base as a long-term knowledge store in a new GA-based design system that learns from experience.…”

Section: Introductionmentioning

confidence: 99%

Case injected genetic algorithms for learning across problems

Louis¹

2004

Engineering Optimization

View full text Add to dashboard Cite

Genetic algorithms (GAs) augmented with a case-based memory of past design problem-solving attempts are used to obtain better performance over time on sets of similar design problems. Rather than starting anew on each design, a GA's population is periodically injected with appropriate intermediate design solutions to similar, previously solved design problems. Experimental results on configuration design problems: the design of parity checker and adder circuits, demonstrate the performance gains from the approach and show that the system learns to take less time to provide quality solutions to a new design problem as it gains experience from solving other similar design problems.

show abstract

“…This strategy is reminiscent of explanation-based analogical reasoning techniques such as those described in Huhns and Acosta (1987) and Kedar-Cabelli (1987). These analogical reasoning techniques use EBG with an artifically high level of operationality to produce rules " that match any potential analogies.…”

Section: Experiments 2: Weakening the Bias Of The Learnermentioning

confidence: 99%

“…We call this extension of A-EBL analogical A-EBL, or ANA-EBL for short, because of its similarities to the work of Huhns and Acosta (1987) and KedarCabelli (1987). The time required for learning was greater for ANA-EBL; however, the concept learned was more accurate on the test cases, getting fifteen of the sixteen examples right.…”

Section: Experiments 2: Weakening the Bias Of The Learnermentioning

confidence: 99%

Abductive explanation-based learning: A solution to the multiple inconsistent explanation problem

Cohen

1992

Mach Learn

View full text Add to dashboard Cite

Abstract. One problem which frequently surfaces when applying explanation-based learning (EBL) to imperfect theories is the multiple inconsistent explanation problem. The multiple inconsistent explanation problem occurs when a domain theory produces multiple explanations for a training instance, only some of which are correct. Domain theories which suffer from the multiple inconsistent explanation problem can occur in many different contexts, such as when some information is missing and must be assumed: since such assumptions can be incorrect, incorrect explanations can be constructed. This paper proposes an extension of explanation-based learning, called abductive explanation-based learning (A-EBL) which solves the multiple inconsistent explanation problem by using set covering techniques and negative examples to choose among the possible explanations of a training example. It is shown by formal analysis that A-EBL has convergence properties that are only logarithmically worse than EBL/TS, a formalization of a certain type of knowledge-level EBL; A-EBL is also proven to be computationally efficient, assuming that the domain theory is tractable. Finally, experimental results are reported on art application of A-EBL to learning correct rules for opening bids in the game of contract bridge given examples and an imperfect domain theory.

show abstract

Argo: An Analogical Reasoning System for Solving Design Problems

Cited by 23 publications

References 22 publications

The design process: properties, paradigms, and structure

The design process: properties, paradigms, and structure

Case injected genetic algorithms for learning across problems

Abductive explanation-based learning: A solution to the multiple inconsistent explanation problem

Contact Info

Product

Resources

About