Fig 5 - uploaded by Mihai Oltean
Content may be subject to copyright.
The cumulative probability of success and the computational effort for the even-5 parity problem. Results are averaged over 100 runs.
Source publication
A genetic programming (GP) variant called traceless genetic programming (TGP) is proposed in this paper. TGP is a hybrid method combining a technique for building the individuals and a technique for representing the individuals. The main difference between TGP and other GP techniques is that TGP does not explicitly store the evolved computer progra...
Context in source publication
Citations
... Yet another approach in GP for learning Boolean even-N-parity functions is called Traceless Genetic Programming (TGP) (Oltean, 2004). TGP is a novel method combining a technique for building individuals and a technique for representing individuals. ...
... Fitness evaluation: the set of fitness cases for the problems of concern consist of 2 k combinations of the k Boolean arguments. So, the fitness is the sum, over these fitness cases, of the Hamming distance (error) between the returned values by MGE chromosome and the correct value of the Boolean function (Oltean 2004 Figures 6, 7, 8 compare these three methods with respect to time complexity. These figures, on the one hand, demonstrate that MGE has almost the same ability (refer to the shape of fitness profiles and the ultimate approximate solutions) as the other two GEs to generate the desired result, and the advantage in efficiency over the others. ...
Grammatical evolution (GE) is a combination of genetic algorithm and context-free grammar, evolving programs for given problems by breeding candidate programs in the context of a grammar using genetic operations. As far as the representation is concerned, classical GE as well as most of its existing variants lacks awareness of both syntax and semantics, therefore having no potential for parallelism of various evaluation methods. To this end, we have proposed a novel approach called model-based grammatical evolution (MGE) in terms of grammar model (a finite state transition system) previously. It is proved, in the present paper, through theoretical analysis and experiments that semantic embedded syntax taking the form of regex (regular expression) over an alphabet of simple cycles and paths provides with potential for parallel evaluation of fitness, thereby making it possible for MGE to have a better performance in coping with more complex problems than most existing GEs.
... El primer enfoque consiste en tomar el algoritmo original de GP (o alguna de sus variantes) y utilizar el otro algoritmo para optimizar los parámetros de los individuos. Como técnica de optimización se ha usado: regresión difusa [29]; búsqueda tabú [30] [37]; el algoritmo de maximización de la expectativa [33]; mínimos cuadrados ortogonales [35]; optimización ordinal [42]; afinación aritmética [36]; regresión polinómica evolutiva (EPR) [40]; redes neuronales (NN) [41]; algoritmo de separación de híper volúmenes [39]; algoritmos genéticos en su versión clásica [44][49] y con selección μ + λ [43]; y la programación genética no ruteada [47]. El segundo enfoque se basa en tomar como base el otro algoritmo (no GP) y reemplazar los individuos u objetos de análisis por los individuos de GP; en los estudios seleccionados se reportaron las siguientes hibridaciones de GP con: el algoritmo de colonia de abejas [28]; el algoritmo de optimización de colonia de hormigas [31], el algoritmo de recocido simulado [32] [45][46], el algoritmo de programa de línea recta [34], NN [38] y el algoritmo de perturbación de series de tiempo [48]. ...
Objective: The aim of this paper is to analyze the main research areas in Genetic Programming (GP). Method: We used the systematic literature review method employing an automatic search with manual refining of papers published on GP between 1992 to 2012. Results: Just 63 studies meet all the requirements of the inclusion criteria. Conclusion: Although studies relating to the application of genetic programming in the forecast of time series were frequently presented, we find that the studies proposing changes in the original algorithm of GP with a theoretical support and a systematic procedure for the construction of model were scarce in the time 1992-2012.
... Specifically in Table 4 we compare the computational effort for BR and PP with the same for the canonical GP [1], Evolutionary Programming [36], Traceless GP [37], Cartesian GP [38] and Size Fair and Homologous Crossover GP [39]. ...
This paper proposes Polyandry, a new nature-inspired modification to canonical Genetic Programming (GP). Polyandry aims to improve evolvability in GP. Evolvability is a critically important GP trait, the maintenance of which determines the arrival of the GP at the global optimum solution. Specifically evolvability is defined as the ability of the genetic operators employed in GP to produce offspring that are fitter than their parents. When GP fails to exhibit evolvability, further adaptation of the GP individuals towards the global optimum solution becomes impossible.
Polyandry improves evolvability by improving the typically disruptive standard GP crossover operator. The algorithm employs a dual strategy towards this goal. The chief part of this strategy is an incorporation of genetic material from multiple mating partners into broods of offspring. Given such a brood, the offspring in the brood then compete according to a culling function, which we make equivalent to the main GP fitness function. Polyandry’s incorporation of genetic material from multiple GP individuals into broods of offspring represents a more aggressive search for building block information. This characteristic of the algorithm leads to an advanced explorative capability in both GP structural space and fitness space. The second component of the Polyandry strategy is an attempt at multiple crossover points, in order to find crossover points that minimize building block disruption from parents to offspring. This strategy is employed by a similar algorithm, Brood Recombination.
We conduct experiments to compare Polyandry with the canonical GP. Our experiments demonstrate that Polyandry consistently exhibits better evolvability than the canonical GP. As a consequence, Polyandry achieves higher success rates and finds solutions faster than the latter. The result of these observations is that given certain brood size settings, Polyandry requires less computational effort to arrive at global optimum solution than the canonical GP.
We also conduct experiments to compare Polyandry with the analogous nature-inspired modification to canonical GP, Brood Recombination. The adoption of Brood Recombination in order to improve evolvability is ubiquitous in GP literature. Our results demonstrate that Polyandry consistently exhibits better evolvability than Brood Recombination, due to a more explorative nature of the algorithm in both structural and fitness space. As a result, although the two algorithms exhibit similar success rates, the former consistently discovers global optimum GP solutions significantly faster than the latter. The key advantage of Polyandry over Brood Recombination is therefore faster solution discovery. As a consequence Polyandry consistently requires less computational effort to arrive at the global optimum solution compared to Brood Recombination.
Further, we establish that the computational effort exerted by Polyandry is competitively low, relative to other Evolutionary Algorithm (EA) methodologies in literature. We conclude that Polyandry is a better alternative to both the canonical GP as well as Brood Recombination with regards to the achievement and maintenance of evolvability.
... Traceless Genetic Programming (TGP) [7] is a hybrid method combining a technique for building the individuals and a technique for representing the individuals. TGP does not explicitly store the evolved computer programs. ...
... TGP does not explicitly store the evolved computer programs. Table 3 shows the results for Traceless GP (TGP) [7]. The results of normal GP are not given because according to [7], [8], LSGP and TGP all out performed normal GP. ...
... Table 3 shows the results for Traceless GP (TGP) [7]. The results of normal GP are not given because according to [7], [8], LSGP and TGP all out performed normal GP. Table 4 shows the average number of generations and standard deviation for Basic OOGP solving the even parity problem for orders 3 to 9. As can be observed, Basic OOGP solves the even parity problem in all runs (i.e., is 100% successful) and solves the problem in a fraction of the number of evaluations used in successful runs of the LSGP or TGP. ...
This paper applies object-oriented concepts to genetic programming (GP) in order to improve the ability of GP to scale to
larger problems. A technique called Basic Object-Oriented GP (Basic OOGP) is proposed that manipulates object instances incorporated
in a computer program being represented as a linear array. Basic OOGP is applied to the even-parity problem and compared to
GP, Liquid State GP and Traceless GP. The results indicate that OOGP can solve certain problems with smaller populations and
fewer generations.
... The main difference between Traceless Genetic Programming (TGP) [1,108] and the standard GP is that TGP does not explicitly store the evolved chromosomes. Instead, the TGP individuals stores only the fitness value(s) achieved so far. ...
Genetic Algorithms and Genetic programming have been used extensively in Evolutionary robotics (ER) with the goal of automatic programming of robotic controllers and has shown to be a promising approach. In this paper, we demonstrate the use of Gene Expression Programming, GEP, a newly developed evolutionary algorithm akin to GA and GP, to evolve robotic behaviours. We use the already well known obstacle avoidance behaviour for our initial work. The behaviour can be regarded as emergent when the main aim is to develop a wandering/exploratory behaviour. From our investigations, we show that GEP is able to learn controllers for a number of different environments. Moreover, standard GEP has never been used before in evolving robotic behaviours, however due to its reported good performances in other fields, we feel it has the capability to be used in ER.
... There are many more other variants explored by various researchers such as the gene expression programming (GEP), gene estimated gene expression programming (GEGEP) an extension to GEP [49], Multi niche parallel GP [74], directed acyclic graphs (DAGS) [82], parallel automatic induction of machine code with genetic programming (parallel AIM-GP) [174], genetic network programming (GNP) [89], grammar model-based program evolution (GMPE) [102] and many others [3,11,101,144,203]. There are also many various hybrids that have been researched, such as genetic programming neural network (GPNN) [193,194], Ant Colony Programming [22], traceless genetic programming (TGP) [175]. Many researchers have looked into improving the newly proposed hybrid. ...
The genetic programming (GP) paradigm, which applies the Darwinian principle of evolution to hierarchical computer programs,
has been applied with breakthrough success in various scientific and engineering applications. However, one of the main drawbacks
of GP has been the often large amount of computational effort required to solve complex problems. Much disparate research
has been conducted over the past 25 years to devise innovative methods to improve the efficiency and performance of GP. This
paper attempts to provide a comprehensive overview of this work related to Canonical Genetic Programming based on parse trees
and originally championed by Koza (Genetic programming: on the programming of computers by means of natural selection. MIT,
Cambridge, 1992). Existing approaches that address various techniques for performance improvement are identified and discussed
with the aim to classify them into logical categories that may assist with advancing further research in this area. Finally,
possible future trends in this discipline and some of the open areas of research are also addressed.
... TGP is a special GP variant which stores only the output of the current program. The speed of the Solvers will be increased significantly in this case as shown in (17). (iii) Using Artificial Neural Networks (9) for some parts (Decision Maker and Problem Solvers) of the A-Brain system. ...
An intelligent system should be able to solve a wide range of problems from different domains. In this paper we propose a complex and adaptive system capable of solving various data analysis problems without needing human help for parameter settings. The system, called A-Brain, consists of several interconnected components (a decision-maker, a trainer, and several problem solvers) which provide a base for building complex problem solvers. The parameters of the trainer's algorithm are problem independent. This fact is a requirement for intelligent systems which cannot rely on human intervention while operating. The A-Brain system is used to solve some well-known problems in the field of symbolic regression and classification. Numerical experiments show that the A-Brain system is able to perform very well on the considered test problems.
... In this paper, several combinational circuits have been considered for use in simulations. First of all, the benchmarks usually used within the EHW community were considered, i.e., multipliers, used in [13], [44], [49], [70], [88], [94], and [95], and parity circuits, used in [30], [85] [87], and [108]. ...
Evolvable hardware (EHW) refers to self-reconfiguration hardware design, where the configuration is under the control of an evolutionary algorithm (EA). One of the main difficulties in using EHW to solve real-world problems is scalability, which limits the size of the circuit that may be evolved. This paper outlines a new type of decomposition strategy for EHW, the "generalized disjunction decomposition" (GDD), which allows the evolution of large circuits. The proposed method has been extensively tested, not only with multipliers and parity bit problems traditionally used in the EHW community, but also with logic circuits taken from the Microelectronics Center of North Carolina (MCNC) benchmark library and randomly generated circuits. In order to achieve statistically relevant results, each analyzed logic circuit has been evolved 100 times, and the average of these results is presented and compared with other EHW techniques. This approach is necessary because of the probabilistic nature of EA; the same logic circuit may not be solved in the same way if tested several times. The proposed method has been examined in an extrinsic EHW system using the (1 + lambda) evolution strategy. The results obtained demonstrate that GDD significantly improves the evolution of logic circuits in terms of the number of generations, reduces computational time as it is able to reduce the required time for a single iteration of the EA, and enables the evolution of larger circuits never before evolved. In addition to the proposed method, a short overview of EHW systems together with the most recent applications in electrical circuit design is provided.
... The main difference between Traceless Genetic Programming and GP is that TGP does not explicitly store the evolved computer programs [15]. TGP is useful when the trace (the way in which the results are obtained) between the input and output is not important. ...
Evolutionary computation, offers practical advantages to the researcher facing dificult optimization problems. These advantages are multi-fold, including the simplicity of the approach, its robust response to changing circumstance, its flexibility, and many other facets. The evolutionary approach can be applied to problems where heuristic solutions are not available or generally lead to unsatisfactory results. As a result, evolutionary computation have received increased interest, particularly with regards to the manner in which they may be applied for practical problem solving.
