B.J. Ross, "Logic-based genetic programming with definite clause translation grammars," in Proc. GECCO-99, edited by J.R. Koza et al., 1999.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....without increasing discrepancy and commonly reducing the complexity of the grammar. Merging involves the merging of two non terminals based upon patterns. When two non terminals are merged, the grammar is often generalised. Some related research includes the work of Dulz et al. 8] and Ross[9]. Dulz infers attribute grammars to model the performance characteristics of protocol implementations but his work differs in that he infers regular grammars and attribute copy rules are used only to define average arrival times of protocol units. Ross uses attribute grammars in conjunction with ....

Ross, Brian J. 2001, Logic-based Genetic Programming with Definite Clause Translation Grammars, New Generation Computing (in press),

....op(n 1,1) exp(n 1,2) pheromone:1) exp(n,l) n=0 and l=#) pre(n 1,0) exp(n 1,1) pheromone:1) exp(n,l) n=0 and l=#) x(n 1,0) pheromone:1) Fig. 2. Initial rules of the SSDT for generating depth 0 of tree Controlling the size of the tree in terms of depth is not a trivial task for GGGP [21, 24]. However, this SSDT representation provides a natural way to do it. In this example, if the maximum depth is 14, we may simply set the pheromone levels of the following two rules to be 0 at the second last level (n = 13) exp(n,l) n=13 and l=0) exp op exp (pheromone: 0) exp(n,l) n=13 and ....

B. J. Ross. Logic-based genetic programming with definite clause translation grammars. In W. Banzhaf, J. Daida, A. E. Eiben, M. H. Garzon, V. Honavar, M. Jakiela, and R. E. Smith, editors, Proceedings of the Genetic and Evolutionary Computation Conference, volume 2, page 1236, Orlando, Florida, USA, 13-17 July 1999. Morgan Kaufmann.

No context found.

B.J. Ross, "Logic-based genetic programming with definite clause translation grammars," in Proc. GECCO-99, edited by J.R. Koza et al., 1999.

No context found.

) B.J. Ross. Logic-based Genetic Programming with Definite Clause Translation Grammars. New Generation Computing, 2001. In press.

....testing sets are composed of random sequences of codons. Each negative example is the size of a typical positive sequence. The negative sets are the same size as the respective training and testing sets for the protein in question. 2. 3 GP Parameters The DCTG GP genetic programming system is used [11]. DCTG GP is a grammatical GP system implemented in Prolog. The target language is defined with a definite clause translation grammar (DCTG) which is a logic based attribute grammar. The SRE DNA grammar in figure 1 is directly encoded in the system with DCTG rules. These rules also include the ....

....6 Lamarckian elite set size 10 Lamarckian hill climbing limit 5 the subset of amino acid codons, determined by the alphabet used in the positive training examples. Crossover and mutation use the methods commonly applied by grammatical GP systems that denote programs with derivation trees; see [11] for details. Some SRE specific crossover and mutation operators are used. SRE crossover permits mask elements in two parents to be merged together. SRE mutation implements a number of numeric and mask mutations, for example, number perturbation, and mask element insertion, deletion, and ....

B.J. Ross. Logic-based Genetic Programming with Definite Clause Translation Grammars. New Generation Computing, 19(4), 2001, 313--337.

....E executes once, after which it behaves like Kleene closure. It is an abbreviation for: E f j E : E f (Ross 2000) evolves SRE expressions using genetic programming. There, SRE is implemented in the DCTGGP system, which is a genetic programming system using a logic based attribute grammar (Ross 1999). The operational semantics of SRE operators are encoded in terms of semantic attributes in the context free grammar of the language. The determination of membership properties (i.e. computed probabilities) of SRE expressions can be determined in polynomial time, since regular expression membership ....

Ross, B.J. (1999). Logic-based Genetic Programming with Definite Clause Translation Grammars. Technical Report CS-99-02. Brock University, Dept. of Computer Science.

....E executes once, after which it behaves like Kleene closure. It is an abbreviation for: E f j E : E f (Ross 2000) evolves SRE expressions using genetic programming. There, SRE is implemented in the DCTGGP system, which is a genetic programming system using a logic based attribute grammar (Ross 1999). The operational semantics of SRE operators are encoded in terms of semantic attributes in the context free grammar of the language. The determination of membership properties (i.e. computed probabilities) of SRE expressions can be determined in polynomial time, since regular expression membership ....

Ross, B.J. (1999). Logic-based Genetic Programming with Definite Clause Translation Grammars.

.... E 0 : E f (ff 6= ffl) Strings 1 E (ff;p) Gamma ffl E (ff;p) ffl Strings 2 E (ff;p) Gamma E 0 E 0 (s;q) E 00 E (ffs;pq) E 00 Figure 1: Transitional semantics of SRE implementation uses a logical grammar definition of SRE, which is part of the DCTGGP system (Ross 1999) (see Section 4) Prolog s backtracking is advantageously used to investigate different paths of an expression s derivation. In addition, string recognition is performed by pattern matching on an argument string and the generated string as shown in the transitional semantics: when a match occurs, ....

....and may even erroneously reject legal strings. However, for many experiments, especially with large strings to be recognized, this speeds up processing significantly. 4 GENETIC PROGRAMMING SYSTEM 4. 1 Grammatical SRE and gSRE The GP system used for the SRE experiments is the DCTG GP system (Ross 1999). DCTG GP performs grammar based genetic programming, in which the target language of the evolved program population is defined in terms of a context free grammar (Lucas 1994, Whigham 1995, Wong and Leung 1995, Geyer Shulz 1997) A major advantage of grammatical GP systems is that the search ....

Ross, B.J. (1999). Logic-based Genetic Programming with Definite Clause Translation Grammars. In: Proc. GECCO-99 (J.R. Koza et al, Ed.).

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