Wolfgang Banzhaf, Peter Nordin, Robert E. Keller, and Frank D. Francone. Genetic Programming -- An Introduction. Morgan Kaufmann, 1998.  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... of which can be traced back to earlier attempts of evolving electronic circuits [12, 18, 25, 16, 15] The computational model has some similarities with other graph based forms of Genetic Programming such as Parallel Distributed Genetic Programming proposed by [21] and represents a dataflow graph [2]. 2.1. The Evolutionary Algorithm The algorithm deals with a population of programs that are instances of a particular program. The population consists of genotypes. Initially the elements of the population are chosen at random. Once the fitness values of the genotypes are evaluated a ....

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming: An Introduction. Morgan Kaufmann, San Francisco, CA, 1998.

....with discussing the applicability of genetic programming to automatic timetabling. Given that evolutionary algorithms and genetic algorithms have been successfully investigated for solving timetabling problems for many years[1] 2] 3] 4] 5] we are interested as to whether genetic programming[6], an evolutionary algorithm similar in some respects to genetic algorithms, would be suitable and bene cial for timetabling. The authors do not know the answer to this question but intend to explore and discuss it in the presentation. The eld of genetic programming mainly di ers from genetic ....

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming: An Introduction. Morgan Kaufmann, Inc., San Francisco, USA, 1998.

....the recombination be meaningful, or to use a simple metaphor, a child should not consist of two heads and no body. 1.3 Genetic Programming Artificial evolution can be applied to any structure that can be represented within a computer. This includes computer programs. Genetic programming (GP) [16, 15, 17, 6] is an approach in evolutionary computation that evolves programs and other executable structures. The original GP algorithm was designed by Koza [16] and many aspects of it, including the representation, remain standard in modern GP. In Koza s GP, programs are represented by their parse tree. A ....

Wolfgang Banzhaf, Peter Nordin, Robert E.Keller, and Frank D.Francone. Genetic Programming - An Introduction. Morgan Kaufmann, 1998.

....one specified explicitly in a language designed for the purpose; if the bias is simply encoded implicitly in the search mechanism, it is said to be procedural. An inductive bias is static if it does not change during the learning process; otherwise it is dynamic. A genetic programming (GP) system [1, 11] can be seen as an inductive learning system. In a GP system, fitness based selection, the bias towards programs that perform well on the problem, is a selection bias. The language bias is implemented through the selection of the function and terminal sets, and the search bias is implemented with ....

Banzhaf W., Nordin P., Keller R.E., and Francone F.D.: Genetic Programming: An Introduction. Morgan Kaufmann Pub (1998).

....( 17] automatically determine the number of such subprograms, the number of arguments that each possesses, and the nature of the hierarchical references, if any, among such automatically defined functions. For current research in genetic programming, see [12] 4] 34] 33] 22] and [5]. A computer program is not a design. Genetic programming can be applied to circuits if a mapping is established between the program trees (rooted, point labeled trees that is, acyclic graphs with ordered branches) used in genetic programming and the linelabeled cyclic graphs germane to ....

Banzhaf, Wolfgang, Nordin, Peter, Keller, Robert E., and Francone, Frank D. 1997. Genetic Programming -- An Introduction. San Francisco, CA: Morgan Kaufmann and Heidelberg: dpunkt.

....genetic programming implementations because learning occurs at the machine code level. The AIM GP system represents individuals as machine code programs. AIM GP uses C code operations to act directly on registers. This means that, in effect, AIM GP generates a subset of C as its program output [5]. One can still constrain the operations on registers to produce effects similar or identical to higher level primitives often used in GP. For example, one might use a sequence of code to compute the Cosine of some value. In this case, a high level mutation could introduce this block of code or ....

W. Banzhaf, P. Nordin, R.E. Keller, and F.D. Francone. Genetic Programming: An Introduction. Morgan Kaufmann, San Francisco, CA, 1998.

....requirement in standard genetic programming (GP) and sets syntactical constraints on programs. GGGP has demonstrated high performance on a number of problems in structured domains [12, 13] and it has been considered as one of the most promising areas in the field of research on genetic programming [3]. In [2] Antonisse made a conjecture that genetic learning guided by a context free grammar would work better if the grammar is unambiguous. The work in this paper was triggered by asking whether the conjecture holds true for GGGP. We have previously observed [7] that most applications of grammar ....

....will also be given. 2.1 Genetic Programming Genetic programming (GP) is an evolutionary algorithm, in which computer programs are the evolutionary targets. An early definition, model, techniques and problems of genetic programming can be found in [8] For a good survey of genetic programming, [3] is recommended. A basic genetic programming system consists of five basic components [8] representation for programs (called genome structure) a procedure to initialize a population of programs, a fitness function to evaluate the performance of the program, genetic operators, and parameters. In ....

[Article contains additional citation context not shown here]

W. Banzhaf, P. Nordin, R.E. Keller, and F.D. Francone, Genetic Programming: An Introduction, Morgan Kaufmann, USA, 1998.

....PC processors (e.g. Intel MMX and AMD 3DNow technologies) However, designing algorithms that can effectively exploit that property to perform complex tasks is not always easy. This makes automatic code generation approaches, such as Genetic Programming (GP) very appealing. Genetic Programming [1, 2] is an Evolutionary Computation (EC) paradigm in which individuals are programs, typically encoded by syntactic trees or, equivalently, prefix notation functions like LISP functions. GP is usually much more computationally intensive than Genetic Algorithms (GAs) although the two evolutionary ....

.... LSB is considered to be adjacent to the MSB) shift operators with variable shift direction (left or right) and entity (1, 2, or 4 bits) The terminal set was composed by four unsigned long integers into which the input data is encoded, and two unsigned long integer ephemeral random constant (ERC) [1, 2], that can take values within the whole range of 32 bit unsigned integers, and in the range [0,16) respectively. Function set Terminal set Function Arity Notes AND 2 bitwise AND OR 2 bitwise OR XOR 2 bitwise XOR NOT 1 bitwise NOT N32 1 logical NOT (C language operator) SH 1 ....

[Article contains additional citation context not shown here]

W. Banzhaf, F. Francone, J. Keller, and P. Nordin. Genetic Programming: An Introduction. Morgan Kaufmann (1998).

....[55] Many pointers to learning by chunking, learning by macros, hierarchical learning, learning by analogy, etc. can be found in Mitchell s book [30] Relatively recent general attempts include program evolvers such as Olsson s Adate [33] and simpler heuristics such as Genetic Programming (GP) [8, 2]. Unlike logic based program synthesizers [12, 57, 9] program evolvers use biology inspired concepts of Evolutionary Computation [34, 48] and Genetic Algorithms [14] to evolve better and better computer programs. Most existing GP implementations, however, do not even allow for programs with loops ....

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming { An Introduction. Morgan Kaufmann Publishers, San Francisco, CA, USA, 1998.

....space and find an efficient representation for the source object to be coded. An interesting way to perform this search is to use evolutionary programming techniques, like genetic programming. The idea is to perform a beam search which is a compromise between exhaustive and hill climbing techniques[2]. An evaluation metric, commonly called a fitness measure, is used to measure the efficiency of each point in the program space. This number is a measure of how well the corresponding program represents the source object. When lossy compression with resource bounds at the decoder is the main ....

....high fitness have a higher probability to participate in crossover operations. The mutation operation simply changes randomly some nodes in the parse trees of individuals of the new generation. The reproduction copies good programs in the new generation. Details of these operations can be found in [2]. What is interesting here is that under general conditions (to be mentioned below) when this process is repeated, the probability to have an element with maximum fitness in the population converges to 1 [4] To see this, note that the dynamic of this algorithm can be modeled Any computer ....

W. Banzhaf, P. Nordin, R. E. Keller and F. D. Francone, "Genetic Programming, An Introduction, " Morgan Kaufmann Publishers, Inc. 1998.

....compression task, in which GenCo was, on average, 80 times faster than a standard C based GP system. 1. Introduction GP is one of the most recent Evolutionary Computation techniques. Its goal is to evolve populations of computer programs, which improve automatically as evolution progresses [Banzhaf 98] Due to the outstanding influence of Kozas seminal book, Genetic Programming: On the Programming of Computers by Means of Natural Selection [Koza 92] it is common, within the Machine Learning community, to associate the term GP to the evolution of tree structures (even when the trees are not ....

....are members of the f set, and the leafs are members of the t set. The interest in GP is growing rapidly, which can be easily explained, if we take into account that automatic programming is expected to be one of the most important tasks in computer science research over the next twenty years [Banzhaf 98] The increase of speed in computer hardware and capability increased exponentially. However, software development was unable to keep up with this growth, and the gap is still increasing. Additionally, the demand for new software is also growing exponentially, but there isnt enough humanpower to ....

[Article contains additional citation context not shown here]

Banzhaf, W., Nordin, P., Keller, E. and Francone, F. D. Genetic Programming --- An Introduction, Morgan Kaufman, 1998.

....Genetic Programming as a linear plan optimiser. We used two di erent hand encoded policy sets for the Blocks Domain in order to seed the initial population with correct but overly long plans. We then used a generational algorithm with standard genetic operators in order to optimise those plans [2]. We based our work on a previously implemented generational algorithm for linear planning [8] The following implementational details have many alternatives, and are not xed. One of the strengths of our approach is that the Fitness Function and Simulation stage can be altered to look for ....

Banzhaf, W., Nordin, P., Keller, R.E., Francone, F.D.: Genetic Programming: An Introduction. San Francisco CA, Morgan Kaufmann Publishers, 1998

....using Genetic Programming as a linear plan optimiser. We used two di erent hand encoded policy sets for the each domain in order to seed the initial population with correct but overly long plans. We then used a generational algorithm with standard genetic operators in order to optimise those plans [2]. We based our work on a previously implemented generational algorithm for linear planning [8] The following implementational details have many alternatives, and are not xed. One of the strengths of our approach is that the Fitness Function and Simulation stage can be altered to look for ....

Banzhaf, W., Nordin, P., Keller, R.E., Francone, F.D.: Genetic Programming: An Introduction. San Francisco CA, Morgan Kaufmann Publishers, 1998

....reproduction, and an addition mutation. To highlight the other major di erences between Genetic Planning and GP we will consider three speci c algorithmic details. 4. 1 Representing a Candidate Chromosome We decided to represent candidates using a linear genome rather than a tree genome [3]. This decision resulted in a considerable speed up and simpli cation of the system [13] The linear genome is a linear list of planning operators and their arguments, much like Fig. 1. Each planning operator and associated arguments makes up an atomic action. Each candidate is made up of these ....

Banzhaf, W., Nordin, P., Keller, R.E., Francone, F.D.: Genetic Programming An Introduction. Morgan Kaufmann Publishers, San Francisco CA (1998)

....One example of software design is the evolution of C programs (O Neill and Ryan, 1999) A large portion of genetic programming has been geared towards analog circuit design such as bandpass filters. Reviews of the research done with genetic programming for analog circuit design can be found in (Banzhaf et al. 1998; Koza et al. 1999) 2.3.6 Robot Evolution. One of the most recent developments in the field of evolutionary design (and artificial life) was reported in (Lipson and Pollack, 2000) This project, called the GOLEM (Genetically Organized Lifelike Electro Mechanical) project, has been described in ....

Banzhaf, W., Nordin, P., Keller, R., and Francone, F. (1998). Genetic Programming: An Introduction. Morgan Kaufmann Publishers.

....Angeline [1] calls these apparently useless fragments of code introns, in analogy with the introns contained in DNA. He points out that the formation of introns should not be hindered, since they provide a better chance for the transfer of complete subtrees during crossover. Banzhaf et al. [2] argue that the analogy to biological introns might be wrong. But since intron is already a common term in the genetic programming domain, we will use it throughout the paper with the meaning of non functional code. Nordin, Francone and Banzhaf [9] demonstrate through experiments that introns ....

....Thus, introns play an important role in evolution, when shielding the exons from destruction through crossover. But they can disappear in the course of evolution. On the other hand, the main source of variability is mutation. From the many existing types of mutation, we consider the following [2, 14, 15]: point mutation change of one base pair to another; neutral mutation a genetic change that is neither advantageous nor disadvantageous for the organism; frameshift mutation insertion or deletion of one or more base pairs; and large DNA sequence rearrangement. Usually, in genetic ....

Wolfgang Banzhaf, Peter Nordin, Robert E. Keller, and Frank D. Francone, Genetic Programming: An Introduction, Morgan Kaufmann, 1998.

....of this structure and knowledge to introduce two new evolutionary formulations of the graph coloring problem. The rst formulation belongs in the class of techniques we normally think of as genetic algorithms [24, 33] while the second one can be thought of as an instance of genetic programming [3, 28]. Our rst approach, described in Section 2, is based on a view of the colorings of G that relates them to the acyclic orientations of G. An acyclic orientation of G is any of the possible ways of assigning directions to the (undirected) edges of G in such a way that no directed cycle is formed ....

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone, Genetic Programming: An Introduction, Morgan Kaufmann Publishers, San Francisco, CA, 1998.

....of DP for constructing rewarding policies [28, 43, 49] EC runs and evaluates policies directly, building new policy candidates from those with the highest evaluations observed so far. EC methods include evolutionary strategies [23, 38] genetic algorithms (GAs) 9] genetic programming (GP) [4, 1], and adaptive extensions of Levin Search [41, 37] EC offers several advantages over DPRL, but also has some drawbacks. I will list advantages first, then point out a major problem of EC, and offer a remedy. EC Advantage 1: No States. Finite time convergence proofs for DPRL [13] require (among ....

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming -- An Introduction. Morgan Kaufmann Publishers, San Francisco, CA, USA, 1998.

No context found.

Banzhaf, W., Nordin, P., Keller, R. E., and Francone, F. D. (1997). Genetic Programming -- An Introduction. On the automatic evolution of computer programs and its applications. Morgan Kaufmann, San Fransisco, and d-punkt, Heidelberg.

No context found.

Banzhaf, W., Nordin, P., Keller, R. E., and Francone, F. D. (1997). Genetic Programming -- An Introduction. On the automatic evolution of computer programs and its applications. Morgan Kaufmann, San Fransisco, and d-punkt, Heidelberg.

No context found.

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming { An Introduction. Morgan Kaufmann, 1998.

....from the areas of symbolic regression and classi cation we showed that the results in these cases were better than randomly chosen parameter sets and could compete with parameter sets chosen with empirical knowledge. 1 Introduction One of the characteristics of Genetic Programming (GP) [10, 5] is the enormous number of free parameters of the algorithm. As di erent problems require different parameter sets GP requires a lot of experience and knowledge on side of the user. In this work we are trying to reduce the number of free parameters. Our aim is to nd adaptive methods that result ....

Banzhaf, W., Nordin, P., Keller, R. E., Francone, F. D.: Genetic Programming: An Introduction. San Francisco, CA: Morgan Kaufmann, 1998

....control capabilities [4] 3.1 Software Architecture The philosophy behind Elvis is that the software architecture should mainly build on evolutionary algorithms and specifically genetic programming. Evolution is thus used to induce programs, functions and symbolic rules for all levels of control [1, 3, 5]. Three hierarchical layers are used for control: Reactive Layer Model Building Layer Reasoning Layer 314 Fig. 1. The Elvis Humanoid Robot Reactive Layer The first layer is a reactive layer based on on line evolution of machine code. This method assumes that all fitness feedback is ....

Banzhaf, W., Nordin, P., Keller, R. E., and Francone, F. D. (1997). Genetic Programming -- An Introduction. On the automatic evolution of computer programs and its applications. Morgan Kaufmann, San Fransisco, and d-punkt, Heidelberg.

....code will not be changed. Selection and Parallelized Fitness Computation The evaluation of control programs for walking robots in a physical simulation is computationally expensive. To save execution time of an evolutionary cycle we implemented a parallelized evaluation of tournaments (c.f. [3]) A number of crossover, mutation and reproduction tournaments T is scheduled (a tournament consists of a given number of individuals i) according to rates p c ,p m and p r . The list of tournaments is topologically sorted with respect to a partial order which is de ned as follows: T x T y ....

W. Banzhaf, P. Nordin, R Keller, and F. Francone. Genetic Programming | An Introduction. dpunkt/Morgan Kaufmann, Heidelberg/San Francisco, 1998.

....performed as a string crossover between instructions while mutation switches instruction or selected bits within the instruction. In the experiments we use the PowerPC chip from Motorola and the original version of AIM GP without instruction blocks. For further details on AIM GP see (Nordin 1997, Banzhaf et al. . 1998, Nordin et al. 1999) 2.2 Hardware To connect several processors into a parallel computer is not a trivial task. Several different architectures exist. In our experiments we have used the Parsytec Power Explorer, one of the most widespread commercial systems. The power explorer is a MIMD ....

Banzhaf, W., Nordin, P. Keller, R. E., and Francone, F. D. (1998). Genetic Programming An Introduction. On the automatic evolution of computer programs and its applications. Morgan Kaufmann, San Francisco and dpunkt Verlag, Heidelberg.

No context found.

Wolfgang Banzhaf, Peter Nordin, Robert E. Keller, and Frank D. Francone. Genetic Programming -- An Introduction. Morgan Kaufmann, 1998.

No context found.

W. Banzhaf, P. Nordin, R. E. Keller, & Frank D. Francone, Genetic Programming: An Introduction. San Fransisco, CA: Morgan Kaufmann, 1998.

No context found.

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming An Introduction. Morgan Kaufmann Publishiers, Inc, San Francisco, CA, 1998.

No context found.

Banzhaf, W., P. Nordin, R. E. Keller and F. D. Francone #1998#. Genetic Programming - An Introduction. Morgan Kaufmann Publishers. San Francisco, CA.

No context found.

Banzhaf, W., Nordin, P., Keller, R. E., and Francone, F. D. (1998). Genetic Programming: An Introduction. Morgan Kaufmann, Inc., San Francisco, USA.

No context found.

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone, Genetic Programming -- An Introduction. Morgan Kaufmann, 1998.

No context found.

W. Banzhaf, P. Nordin, R.E. Keller, and F.D. Francone. Genetic Programming: An Introduction. Morgan Kaufmann, 1998.

No context found.

W. Banzhaf, P. Nordin, R.E. Keller and F.D. Francone, Genetic Programming--An Introduction, Morgan Kaufmann: San Francisco, 1998.

No context found.

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming { An Introduction. Morgan Kaufmann Publishers, San Francisco, CA, USA, 1998.

No context found.

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone, "Genetic Programming An Introduction," Morgan Kaufmann Publishers, Inc., 1998, pp. 112.

No context found.

Banzhaf, W., Nordin, P., Keller, R. and Francone, F. Genetic Programming: An Introduction. Morgan Kaufmann Publishers, Inc. San Francisco, CA. 1998.

No context found.

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming -- An Introduction. Morgan Kaufmann Publishers, San Francisco, CA, USA, 1998.

No context found.

W. Banzhaf, P. Nordin, R.E. Keller and F.D. Francone, Genetic Programming--An Introduction, Morgan Kaufmann: San Francisco, 1998.

No context found.

W. Banzhaf, P. Nordin, R. Keller, and F. Francone. Genetic Programming: An Introduction. Morgan Kaufmann, 1998.

No context found.

Banzhaf, W. P., R. E. Nordin, Keller, and F. D. Francone. 1998. Genetic programming: An introduction. Morgan Kaufmann, San Francisco, Calif.

No context found.

Banzhaf, W., P. Nordin, R. E. Keller, and F. D. Francone. 1998. Genetic programming: an introduction. Morgan Kaufmann, San Francisco, Calif.

No context found.

W. Wolfgang, P. Nordin, R. E. Keller, and F. D. Francone, Genetic Programming}An Introduction, Morgan Kaufmann, San Francisco, CA and dpunkt, Heidelberg, 1998.

No context found.

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone, Genetic Programming: An Introduction, Morgan Kaufmann, San Francisco, CA, 1998.

No context found.

W. Banzhaf, P. Nordin, R. E. Keller, and F. D. Francone, Genetic Programming: An Introduction, Morgan Kaufmann, San Francisco, CA, 1998.

No context found.

Wolfgang Banzhaf, Peter Nordin, Robert E. Keller, and Frank D. Francone. Genetic Programming: An Introduction. Morgan Kaufmann, San Francisco, CA, 1998.

No context found.

Wolfgang Banzhaf, Peter Nordin, Robert E.Keller, Frank D.Francone, "Genetic Programming - An Introduction", Morgan Kaufmann Publishers, Inc., 1998

No context found.

W. Banzhaf et al, Genetic Programming: An Introduction (Morgan Kaufmann Publishers, San Francisco, 1998)

No context found.

) W. Banzhaf, P. Nordin, R.E. Keller, and F.D. Francone. Genetic Programming: An Introduction. Morgan Kaufmann, 1998.

No context found.

Banzhaf, Wolfgang, Nordin, Peter, Keller, Robert E., and Francone, Frank D. 1998. Genetic Programming --- An Introduction. San Francisco, CA: Morgan Kaufmann and Heidelberg: dpunkt.

No context found.

Wolfgang Banzhaf, Peter Nordin, Robert E. Keller, and Frank D. Francone. Genetic Programming --- An Introduction. Morgan Kaufmann, dpunkt, (1998).

First 50 documents  Next 50

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