Buchanan B, Feigenbaum E. DENDRAL and Meta-DENDRAL: Their applications dimension. Artif Intel 1978;11:5-24.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....then use the knowledge editor to produce specific expert systems for the application area. PROTEGE and ETS are representative of a class of systems aimed at generating expert systems, either from experts or from an existing knowledge base. Other examples of such systems include: META DENDRIL [BUCH78], AQ11 [MICH80] TEIRESIAS [DAVI81] and NANOKLAUS [HASS83] Some researchers have picked up this trail and are attempting to employ expert systems to support domain specific reuse. Iscoe advocates using expert systems to enable users . to directly create and maintain their own programs because ....

B. Buchanan and E. Feigenbaum, "DENDRAL and META-DENDRAL: Their Applications Dimension", Artificial Intelligence, November 1978. 83

....have implemented a system which automatically generates examples for a constraint stated in the theory and we have experimented with the system in the BoyerMoore theorem prover. 1.1 An Overview Examples are, in general, a very useful tool in Artificial Intelligence. Many machine learning systems [52, 33, 10, 14, 32] use examples for the tasks of generating concepts and conjectures. For instance, Winston s system [52] learns structural descriptions from examples. His system is presented with training instances positive examples and near misses of a structure (concept) to be learned such as an arch and ....

....with many possibilities, as opposed to generating a few difficult examples. RELATED WORK 84 7. Related Work Various attempts have been made to generate and apply examples. Examples have long been used for many AI tasks, especially for automated reasoning [19, 20, 2, 40] and machine learning [33, 10, 52, 32, 34]. They are also used in the areas of intelligent computer assisted instruction and tutoring and intelligent human interfaces [54, 41] However, in many cases examples are given by the user interactively or stored initially in the system. In the introductory chapter we described Gelernter s ....

Buchanan, B. G. and Feigenbaum, E. A. "DENDRAL and META-DENDRAL: Their Applications Dimension". Artificial Intelligence 11 (1978), 5-24.

....goal. pg. 17) Many design problem solvers make use of both simulation and optimization to generate designs. In fact, one way to view this coupling is under the general problem solving technique called generate and test, which has been used in a number of design and design like systems [2, 14,17]. The problem encountered in the use of generate and test systems is control of search. Blind generate and test systems might enumeratively explore each possible design, an impossibility given a design of any reasonable complexity. Thus control of search is paramount in such systems. Our approach ....

B.G. Buchanan and E.A. Feigenbaum, "DENDRAL and Meta-DENDRAL: their applications dimension, Artificial Ingelligence, 11(1), 1978, pp. 5-24.

....which one to apply; this is called conflict resolution. 3. Apply the rule, perhaps adding a new item to the working memory or deleting an old one and then go to step 1. Rule based expert systems have been applied successfully in many areas including: medical diagnosis [Shortliffe,76] chemistry [Buchanan,78] and plant pathology [Michalski,80] The rule based approach assumes a number of rules which demand that domain rules are independent of each other; all rules can be applied under one control scheme operated by the inference engine; and rules completely specify their own context of application. ....

Buchanan, B. G. and Feigenbaum, E. A., "DENDRAL and Meta-DENDRAL: Their Applications Dimension," Artificial Intelligence, 11, pp. 5-24, (1978).

....goal. pg. 17) Many design problem solvers make use of both simulation and optimization to generate designs. In fact, one way to view this coupling is under the general problem solving technique called generate and test, which has been used in a number of design and design like systems [4, 26]. The problem encountered in the use of generate and test systems is control of search. Blind generate and test systems might enumeratively explore each possible design, an impossibility given a design of any reasonable complexity. Thus control of search is paramount in such systems. 2 Our ....

B.G. Buchanan and E.A. Feigenbaum, "DENDRAL and Meta-DENDRAL: their applications dimension, Artificial Intelligence, 11(1), 1978, pp. 5-24.

....it maintains the O(e log 2 e) time complexity of IREP. Cohen also estimates the time complexity empirically. A different style of rule learning can be traced back to the search based data mining program MetaDENDRAL (Buchanan, Smith, White, Gritter, Feigenbaum, Lederberg, and Djerassi 1976) (Buchanan and Feigenbaum 1978). Examples of MetaDENDRAL style rule learning include the Brute programs (Riddle, Segal, and Etzioni 1994; Segal and Etzioni 1994a) PVM (Weiss, Galen, and Tadepalli 1990) ITRULE (Smyth and Goodman 1992) the RL programs (Clearwater and Provost 1990; Provost and Buchanan 1995; Fawcett and Provost ....

Buchanan, B. and E. Feigenbaum (1978). DENDRAL and META-DENDRAL: Their applications dimensions. Artificial Intelligence 11, 5--24.

....easy to see that this is the only solution. 3 Related work In this section we put our approach in the perspective of some earlier work and current trends in this area of research. Early expert systems (today often referred to as the first generation expert systems) like MYCIN [8] and DENDRAL [7] was based on a single knowledge representation paradigm, often production rules [8] or frames [12] But perhaps the most important characteristic of these systems was that they did not separate the domain knowledge from the control knowledge. For instance, the MYCIN system used production rules ....

B.G. Buchanan, E.A Feigenbaum, Dendral and Meta-Dendral: their applications dimension, Artificial Intelligence, Vol. 11 (1978), pp. 5-24.

....to show, in finite number of steps, whether P is a theorem or not. 2 Production systems Production systems were first proposed by E. Post in 1943, but their current form was introduced by A. Newell and H.A. Simon in 1972 for psychological modeling and by B.G. Buchanan and E.A. Feigenbaum [52] in 1978 for expert systems. A production system consists of . A knowledge base, also called a rule base, containing production rules. A data base containing facts. A rule interpreter, also called a rule application module, to controle the entire production system. Production rules are ....

B.G. Buchanan and E.A. Feigenbaum, DENDRAL and META-DENDRAL: Their applications dimension, Artificial Intelligence, 11(1978) 5-24.

....over growth, as each rule is grown, the CWS algorithm evaluates it in the context of the currently held rule set. CWS has time complexity of O(e) Domingos approach of conquering without separating is similar to the approach taken by the search based MetaDENDRAL style inductive algorithms [12] [13]. Several rule learners have introduced optimizations to this style of inductive learning. 3 Both RL [21] and BruteDL [66] use search reduction techniques, including pruning and depth bounding, to allow for massive searches of very large rule spaces. Webb [75] introduces techniques for dynamic ....

Buchanan, B.G. and Feigenbaum, E.A. (1978). "DENDRAL and META-DENDRAL: their Applications Dimensions." In Artificial Intelligence, North-Holland, Vol. 11, pp: 5-24.

....projects lacked the expected results. Consequently, research begun to focus on rather specific and narrow application areas, in which knowledge systems were remarkably successful. Significant milestones of early knowledge systems research includes applications to medical diagnosis [27] chemistry [4], and the design of computer systems [17] These and other applications are surveyed in [8,32] The development of dedicated problems solving procedures for different tasks, such as specialized knowledge representation schemes or inference techniques, led to an exhaustive tool box which ....

B.G. Buchanan and Feigenbaum E.A. DENDRAL and meta-DENDRAL: Their applications dimension. Artificial Intellicence, 11:5--24, 1978.

....of the currently held rule set. CWS has time complexity of O(e) Domingos s approach of conquering without separating is similar to the approach taken by search based rule learning algorithms in the style of MetaDENDRAL (Buchanan, Smith, White, Gritter, Feigenbaum, Lederberg, and Djerassi 1976) (Buchanan and Feigenbaum 1978). Several rule learners have introduced optimizations to this style of rule learning. Both RL (Clearwater and Provost 1990) and BruteDL (Segal and Etzioni 1994) use search reduction techniques, including pruning and depth bounding, to allow for massive searches of very large rule spaces. Webb ....

Buchanan, B. and E. Feigenbaum (1978). DENDRAL and META-DENDRAL: Their applications dimensions. Artificial Intelligence 11, 5--24.

.... provides a detailed overview of early uses of search for rule induction, culminating in the de nition of version spaces (described below) Probably the rst successful application of rule space search for knowledge discovery was in the Meta DENDRAL program (Buchanan, Feigenbaum, Lederberg, 1971; Buchanan Feigenbaum, 1978; Buchanan Mitchell, 1978) which performed what would now be called data mining for scienti c discovery in Chemistry. Meta DENDRAL used chemistryspeci c knowledge for pruning, and not only rediscovered known, published rules of mass spectrometry, but also made novel discoveries that were ....

Buchanan, B. G., & Feigenbaum, E. A. (1978). DENDRAL and META-DENDRAL: their applications dimension. Articial Intelligence, 11, 5-24.

No context found.

Buchanan B, Feigenbaum E. DENDRAL and Meta-DENDRAL: Their applications dimension. Artif Intel 1978;11:5-24.

No context found.

B Buchanan and E Feigenbaum. Dendral and MetaDendral: Their applications dimension. Artificial Intelligence, 11, 1978.

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