P. P. Bonissone, Soft computing: the convergence of emerging reasoning technologies, Soft Computing 1 (1) (1997) 6--18.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....techniques we have Fuzzy Logic, Probabilistic Reasoning, Neural Networks and Evolutionary Algorithms. Over the past few years we have seen an increasing number of hybrid algorithms, in which two o more Soft Computing technologies have been integrated to improve the overall algorithm performance [2]. As happens in data mining, if we try to reveal useful information from the data one fundamental step is the preprocessing of the data in order to select the most adequate variables. Within the context of modeling and more concrete fuzzy modeling, the objective is to find a set of relations ....

Bonissone, P., "Soft Computing: The Convergence of Emerging Reasoning Techniques", Journal of Soft Computing, vol. 1, n. 1, 1997.

....dicult decision because the composition of the KB depends directly on the problem being solved. Due to the complexity of the KB derivation, a large quantity of automatic techniques has been proposed to put it into e ect. Many of these techniques are collected under the name of Soft Computing (SC) [31, 32]. SC is a new eld of Computer Science that deals with the integration of problem solving techniques such as Fuzzy Logic, NNs, or GAs. Each of these techniques provides us with complementary reasoning and search methods to solve complex problems. Among all the possible combinations, we are ....

Bonissone, P.P. (1997). Soft computing: The convergence of emerging reasoning technologies. Soft Computing. A Fusion of Foundations, Methodologies, and Applications 1(1), pp. 6-18.

....the problem being solved. The accuracy of the FRBS in solving the problem will directly depend on this task. Due to the complexity of the FRB learning, some automatic techniques have been proposed to put it into e ect. 4 Many of these techniques are collected under the name of Soft Computing [7, 45]. Soft Computing is a new eld of Computer Science that deals with the integration of problem solving techniques such as Fuzzy Logic, Neural Networks, or GAs, among many others. Each of these techniques provides us with complementary reasoning and search methods to solve complex problems. Among ....

P.P. Bonissone, Soft computing: The convergence of emerging reasoning technologies, Soft Computing. A Fusion of Foundations, Methodologies, and Applications 1:1 (1997) 6-18.

....practical. We need the collaboration between them and this is the approach taken by hybrid systems. Over the past few years we have seen 1 an increasing number of hybrid algorithms, in which two or more Soft Computing technologies have been integrated to improve the overall algorithm performance [Bon97]. Those hybrid systems are composed by several different and interchangeable techniques. The best combination of such techniques may vary from problem to problem. This leads us to the idea of a multiple loosely coupled co processing distributed system. Each technique can be developed as a system ....

Bonissone, P., "Soft Computing: The Convergence of Emerging Reasoning Techniques ", Journal of Soft Computing, vol. 1, n. 1, 1997.

....techniques we have Fuzzy Logic, Probabilistic Reasoning, Neural Networks and Evolutionary Algorithms. Over the past few years we have seen an increasing number of hybrid algorithms, in which two o more Soft Computing technologies have been integrated to improve the overall algorithm performance [2]. As in [5] we use the term the Knowledge Discovery in Databases (KDD) to denote the overall process of extracting high level knowledge from low level data and the term Data Mining as the concrete act of extracting patterns or model from data. Hence many steps precede data mining and one of them ....

.... variables p; output: population POP = W 1 = w 1 1 ; w 1 p ) W popsize = w popsize 1 ; w popsize p ) of popsize individuals such that w i j 2 [0; 1] j = 1; p, i = 1; popsize, and p X j=1 w i j = 1, i = 1; popsize; 1] i 1; [2] rnd real random value 2 [0; 1] 3] If rnd 0:5 then weights1(input : p; 1; output : W ) else weights2(input : p; 1; output : W ) 4] W i W ; 5] If i popsize then i i 1; Go to 2; procedure weights1; input: integer number q, with 1 q p; real value val, with 0 val 1; output: ....

[Article contains additional citation context not shown here]

Bonissone, P., "Soft Computing: The Convergence of Emerging Reasoning Techniques", Journal of Soft Computing, vol. 1, n. 1, 1997.

....reasonable limit on the cardinality of the truth value set are often found in applications where the truth values are called linguistic labels , such as Very High, Quite High, High, Very Low. These logics appear in many important applications such as expert systems [52] and fuzzy control [23]. Sometimes a larger (though finite) number of truth degrees is needed; this is the case for discrete optimisation functions, hardware verification [44] approximation of continuous fuzzy sets. When the number of finite truth values or the arity of connectives is truly large, their functions need ....

....In [97] an annotated logic program is derived from a lattice. A general framework for using many valued logic in knowledge representation was given by [36] An application of many valued deduction in description logic is [143] Fuzzy Control Most fuzzy controllers are based on fuzzy rules [23] in which the premise is a conjunction and each conjunct has the form X i is A i , X i denoting an input or state variable of the process to be controlled and A i a fuzzy set. In [41] the different possible semantics for such rules is analysed in a lucid style. Many kinds of functions that ....

P. P. Bonissone. Soft computing: the convergence of emerging reasoning technologies. Soft Computing---A Fusion of Foundations, Methodologies and Applications, 1(1):6-- 18, Apr. 1997.

.... approaches have been presented taking Evolutionary Algorithms (EAs) 1] usually Genetic Algorithms (GAs) 48] as a base, constituting the so called Genetic Fuzzy Rule Based Systems (GFRBSs) 10, 37] These kind of systems are considered nowadays as an important branch of the Soft Computing area [6] in view of the large number of contributions developed in the last few years (see [15] section 3.13, 16] section 13) GFRBSs are based on combining the main feature of the FRBSs, interpolative reasoning, a consequence of the cooperation between the fuzzy rules composing the FRB, and the EAs, ....

P.P. Bonissone, Soft computing: the convergence of emerging reasoning technologies, Soft Computing 1:1 (1997) 6-18.

.... of solving this problem, in the last few years, many different approaches have been presented taking EAs, usually GAs, as a base, to automatically derive the KB, constituting the so called GFRBSs [7] see Figure 2) GFRBSs are considered nowadays as an important branch of the Soft Computing area [5]. The promising results obtained by the EAs in the learning or tuning of the KB have extended the use of these algorithms in the last few years (see [11, 12] It is possible to distinguish among three different groups of GFRBSs depending on the KB components included in the learning process: DB, ....

P.P. Bonissone, "Soft computing: the convergence of emerging reasoning technologies," Soft Computing, vol. 1, no. 1, pp. 6-18, 1997.

....the promising results obtained by the EAs in the learning or tuning of the FRB have extended the use of these algorithms in the design of FRBSs. These kind of GFSs, Genetic Fuzzy Rule Based Systems (GFRBSs) 9, 30] are considered nowadays as an important branch of the Soft Computing area [7] in view of the large number of contributions developed in the last few years (see [14] section 3.13, 15] section 13) In this paper we present a multi stage hybrid GA Evolution Strategy (GA ES) process for designing approximate Mamdani type FRBSs from examples. This GFRBS will allow us to ....

P.P. Bonissone, Soft computing: the convergence of emerging reasoning technologies, Soft Computing 1:1 (1997) 6-18.

No context found.

:to--appear, 1997.

No context found.

P. P. Bonissone, Soft computing: the convergence of emerging reasoning technologies, Soft Computing 1 (1) (1997) 6--18.

No context found.

Bonissone P. P.: Soft computing: the convergence of emerging reasoning technologies. Soft Computing 1 (1) (1997), 6-18.

No context found.

Bonissone, P., "Soft Computing: The Convergence of Emerging Reasoning Techniques", Journal of Soft Computing, vol. 1, n. 1, 1997.

No context found.

Bonissone, P. (1997). "Soft Computing: The Convergence of Emerging Reasoning Techniques", Journal of Soft Computing, vol. 1, n. 1.

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