D. B. Fogel, L. J. Fogel, and V. W. Porto. Evolving neural networks. Biological Cybernetics, 63:487--493, 1990.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....a changing environment. In the literature, research into EANN has been taking one of three approaches; evolving the weights of the network, evolving the architecture, or evolving both simultaneously. The EANN approach uses either binary representation to evolve the weight matrix [12, 13] or real [7, 8, 9, 18, 19, 23]. There is not an obvious advantage of binary encoding in EANN over the real. However, with real encoding, there are more advantages including compact and natural representation. The key problem (other than being trapped in a local minimum) with BP and other traditional training algorithms is the ....

D.B. Fogel, L.J. Fogel, and V.W. Porto. Evolving neural networks. Biological Cybernetics, 63:487--493, 1990.

....First, EPNet emphasises the evolution of ANN behaviors by EP and uses a number of techniques, such as partial training after each architectural mutation and node splitting, to maintain the behavioral link between a parent and its offspring effectively. While some of previous EP systems [3] 10] [12] [15] acknowledged the importance of evolving behaviors, few techniques have been developed to maintain the behavioral link between parents and their offspring. The common practice in architectural mutations was to add or delete hidden nodes or connections uniformly at random. In particular, a ....

D. B. Fogel, L. J. Fogel, and V. W. Porto, "Evolving neural networks," Biol. Cybern., vol. 63, pp. 487--493, 1990.

....neural networks is to use evolutionary search. Genetic algorithms [23,54,56] evolutionary programming [18,20] and evolution strategies [67,69,73] are typical examples of evolutionary search. Attempts at training feedforward neural networks by evolutionary search include the work of Fogel et al. [19], Yao and Liu [87] and Montana and Davis [57] There are also attempts to evolve recurrent networks, e.g. Angeline et al. 3] and McDonnell and Waagen [51] Applying evolutionary search to more complex types of neural networks (high order networks, for example) can be found in [33 35,85] and a ....

D. B. Fogel, L. J. Fogel, and V. W. Porto. Evolving neural networks. Biological Cybernetics, 63:487--493, 1990.

....representations and operators based on the concept of equivalent classes [115] 116] has given representations other than ary strings a more solid theoretical foundation. Real numbers have been proposed to represent connection weights directly, i.e. one real number per connection weight [27] [29], 30] 48] 63] 65] 74] 95] 96] 102] 110] 111] 117] 118] For example, a realnumber representation of the ANN given by Fig. 3(a) could be (4.0,10.0,2.0,0.0,7.0,3.0) As connection weights are represented by real numbers, each individual in an evolving population will be a ....

....One of the major advantages of using mutation based EA s is that they can reduce the negative impact of the permutation problem. Hence the evolutionary process can be more efficient. There have been a number of successful examples of applying EP or ES to the evolution of ANN connection weights [29], 63] 65] 67] 68] 95] 96] 102] 106] 111] 117] 119] 120] In these examples, the primary search operator has been Gaussian mutation. Other mutation operators, such as Cauchy mutation [121] 122] can also be used. EP and ES also allow self adaptation of strategy parameters. ....

D. B. Fogel, L. J. Fogel, and V. W. Porto, "Evolving neural networks," Biological Cybern., vol. 63, no. 6, pp. 487--493, 1990.

....problem in Civil Engineering (Gero et al. 1997; Lunn and Johnson, 1996) Bin packing has also been addressed by other methods, including simulated annealing, and will be discussed in the next section of this chapter. Neural network topologies have been synthesized by numerous researchers (Fogel et al. 1990; FigueiraPujol and Poli, 1998; Hancock, 1990; Kaise and Fujimoto, 1998; Skourikhine, 1998; Wicker et al. 1998; Zhao, 1996) Similarly, many have synthesized fuzzy systems (Garcia et al. 1999; Murata et al. 1998) Fuzzy systems are a type of rule based system, which has also received much ....

Fogel, D. B., Fogel, L. J., and Porto, V. W. (1990). Evolving neural networks. Biolog. Cybern., 63:487--493.

....connection weights between its nodes. Connection weight values appropriate for a given computation may be computed byanumber of di#erent methods, including backpropagation #Rumelhart, et al. 1986# and evolutionary simulations. The latter approach has been explored by Montanta and Davis #1989#, Fogel, et al. #1990# and Whitley, et al. #1990#. Neural networks are a useful tool for modeling the interaction between evolution and learning because they allow the combination of these two methods for determining connection weightvalues #Chalmers, 1991; Belew, et al. 1991#. In each time step of its interaction ....

D. B. Fogel, L. J. Fogel, and V.W. Porto. Evolving neural networks. Biol. Cybern., 63:487#493, 1990.

....earlier) The results for the parity problems compare very favorably with those reported in the literature. To solve the XOR problem the following numbers of generations to attain solutions are reported: 90 [16] 513 [9] less than 100 with a minimal solution at generation 200 [17] less than 40 [18]. For the 3 bit parity problem, Yao et al. 16] reported an average of 739 generations to get a solution. The 4 bit parity solution reported by Zhang et al. 11] was achieved in fewer generations (9) but a population of 1000 individuals was used, and training by a hillclimbing procedure was ....

D. Fogel, L. Fogel, and V. Porto. Evolving neural networks. Biological Cybernetics, 63:487--493, 1990.

....Int. Artif. Intell. Neural Netw. Complex Probl. Solving Technol. Netherlands) 467] Applied Mathematics and Computation, 590] Artif. Intell. Eng. UK) 424, 512] Artificial Life, 63, 301, 305, 556] Autom. Electr. Power Syst. China) 488] Bioinformatics, 588] Biological Cybernetics, [681, 835] Biophysical Journal, 126, 173] Bull. Fac. Eng. Univ. Tokushima (Japan) 336] Bull. Sci. Assoc. Ing. Electr. Inst. Electrotech. Montefiore, 633] Bulletin of the Polish Academy of Sciences Chemistry, 100] Cancer Letters, 313] Chemometrics and Intelligent Laboratory Systems, 149, 495, ....

....Fariselli, Piero, 224, 558] Fekadu, Adhanom A. 761] Feldman, David S. 675] Ferguson, J. J. 676] Filelis, A. 871] Fleischhauer, T. 407] Fleming, Peter J. 589] Floreano, Dario, 677] Floyd, C. E. 160] Fogarty, Terence C. 241, 378, 436, 471, 474, 678] Fogel, David B. [83, 276, 282, 313, 315, 679, 680, 681, 682, 683, 684, 685, 686, 687, 688, 689, 690, 691, 692] Fogel, Lawrence J. 276, 681, 685, 687, 691] Foo, Shou King, 170] Forst, C. V. 248] Fortuna, L. 639, 640] Foy, Mark, 693] Foy, M. 694] Franco, Aurali B. 888] Fredriksson, Kimmo, 496, 517] Freedman, M. T. 487] Freisleben, Bernd, 695] French, I. G. 171] Frenzel, James ....

[Article contains additional citation context not shown here]

David B. Fogel, Lawrence J. Fogel, and Vincent W. Porto. Evolving neural networks. Biological Cybernetics, 63(6):487--493, 1990. y(Fogel/bib) ga:Fogel90g.

....and Computers, 84] total 2 books 4.2 Journal articles The following list contains the references to every journal article included in this bibliography. The list is arranged in alphabetical order by the name of the journal. AI Expert, 24, 25] AIAA Journal, 141] Biological Cybernetics, [28, 92, 98, 116, 294] Chemiker Zeitung, 140] COMPEL The International Journal for Computations and Mathematics in Electrical and Electronic Engineering, 302] Complex Systems, 33, 117, 118, 175, 227, 232] Computers in Biology and Medicine, 37, 249] Computers Industrial Engineering, 38, 293] Electronic ....

....[204] Ebeling, Werner, 83] Eckardt, H. 147] Eggert, H. 85] Elia, Paul V. 139] Eshelman, Larry J. 264] Farmer, J. Doyne, 86] Feldberg, Rasmus, 246] Feldhousen, E. L. 51] Ferri, F. 13, 14] Flowers, Margot, 164] Fogarty, Terence C. 87, 88, 89, 90, 91] Fogel, David B. [92, 93, 94, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107] Fogel, Lawrence J. 95, 97, 98, 104, 105, 106] Fontana, Walter, 108] Forrest, Stephanie, 109, 110] Frazer, L. N. 192] Freeman, L. M. 169, 170] Galarce, Carlos E. 114] Garis, Hugo de, 303, 304, 305, 306, 307, 308, 309, 310] Geary, R. A. 81] Gerys, D. 280] Glesner, M. ....

[Article contains additional citation context not shown here]

David B. Fogel, Lawrence J. Fogel, and Vincent W. Porto. Evolving neural networks. Biological Cybernetics, 63(6):487--493, 1990. y(Fogel/bib) ga:Fogel90g.

....computational cost. 6 c c c c c c c c c Fig 4:An optimized network topology for the parity problem. An optimized topology for the parity problem is shown in Figure 4, which is much simpler than that in [10] By the way, we also test the algorithm on the gasoline blending problem from [3],the XOR problem and the symmetry problem. It is indicated that our approach to designing neural networks can be used in evolving both their structures and weights successfully. 4 Conclusions This paper presents an evolutionary approach to designing neural networks both for their topology and ....

D.B.Fogel,L.J.Fogel and V.W.Porto, Evolving Neural Networks,Biol.Cybern.,63,487--493,1990.

....node are placed together [124] or the input and the output weights of a node are next to each other [99] The use of binary coding has the disavantage of numerical precision, as well as the sometimes big structures of strings. For this reason real coding representation may be used alternatively[29]. After the representation scheme has been decided, the genetic algorithms can evaluate each chromosome of the population. Usually the most commonly used fitness function is derived by means of the squared error of the training patterns. Actually, the fitness is obtained via appropriate ....

D.B. Fogel, L.J. Fogel, and V.W. Porto. Evolving Neural Networks. Biological Cybernetics, 63:487--493, 1990.

....or even continuous since EAs do not depend on gradient information. Because EAs can treat large, complex, nondifferentiable and multimodal spaces, which are the typical case in the real world, considerable research and application has been conducted on the evolution of connection weights [24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112]. The evolutionary approach to weight training in ANNs consists of two major phases. The first phase is to decide the representation of connection weights, i.e. whether in the form of binary strings or not. The second one is the evolutionary process simulated by an EA, in which search operators ....

....6 Gamma Gamma Gamma Gamma Gamma Gamma Delta Delta Delta Delta Delta Delta A A A A A AK 2 10 4 3 7 0010 0000 0100 1010 0011 0111 Figure 4: a) An ANN which is equivalent to that given in Figure 3(a) b) Its binary representation under the same representation scheme. connection weight [27, 29, 30, 48, 117, 63, 64, 65, 95, 96, 74, 111, 102, 110, 118]. For example, a realnumber representation of the ANN given by Figure 3(a) could be (4.0,10.0,2.0,0.0,7.0,3.0) As connection weights are represented by real numbers, each individual in an evolving population will be a real vector. Traditional binary crossover and mutation can no longer be used ....

[Article contains additional citation context not shown here]

D. B. Fogel, L. J. Fogel, and V. W. Porto, "Evolving neural networks," Biological Cybernetics, vol. 63, pp. 487--493, 1990.

....sigmoidal [42] and radial [47] basis functions. Within this framework of competition among separate neural networks, other differentiating factors include the basic alphabet of binary or real valued representations which encode the specification of a neural network for genetic [48] or non genetic [35] evolution. B. Evolving One Hidden Unit at a Time Cascade correlation learning [49] and similar methods such as projection pursuit learning [50] employ nontraditional neural network architectures in which the hidden units are added sequentially. The cascade correlation architecture does not ....

D. B. Fogel, L. J. Fogel, and V. W. Porto, "Evolving neural networks," Biological Cybernetics, vol. 63, pp. 487--493, 1990.

....and (3) the endgame of the two player game Nine Men s Morris [2] employing a (23 12 1010) topology, a (3 20 3) topology and a (120 60 20 21) topology, respectively. So at least the last one of them is much more complex than problems considered in publications on comparable topics ( 3] 4] [5], 6] 7] 8] 9] 10] 11] 12] 13] 14] 15] Arguing with Miller et.al. 9] the search space of possible network topologies is infinitely large, not differentiable, complex, noisy, deceptive and multimodal. These attributes make random, enumerative, gradient descent or heuristic ....

D.B. Fogel, L.J. Fogel, V.W. Porto, Evolving neural networks, in: Biological Cybernetics 63 (Springer, Berlin, 1990)

....Elman, and Parisi (1990) Our purpose in this simulation is to see whether near bifurcation dynamics discussed in the previous section can actually improve creatures performance in a non stationary environment where selection and memory of sensory input is necessary. Evolutionary programming (Fogel, Fogel, and Porto 1990) was used to optimize the recurrent network that controls the movement of the creature. Figure 5 shows an example of the grid like world. There were a certain number of food items in fixed positions, each of which turned visible or invisible in a stochastic fashion, as determined by a two state ....

Fogel, D., L. Fogel, and V. Porto (1990). Evolving neural networks. Biological Cybernetics 63, 487--493.

....large mutation steps: the larger the value K, the less the probability of taking large steps. K also determines the smallest step size R i Delta 2 GammaK . The exponential mutation is contrasted with the Gaussian mutation implemented in evolution strategies and evolutionary programming (Fogel, Fogel and Porto, 1990) such that very large steps take place with only a small probability. Due to the large costs for local search, we have used various heuristics for applying local search. One heuristic is to use local search immediately after fitness evaluation to some portion, say top 50 , of the population ....

Fogel, D. B., Fogel, L. J. and Porto, V. W. (1990). Evolving neural networks. Biological Cybernetics, 63:487--493.

....is evolutionary algorithms (EA) based on simulated evolution. Evolutionary algorithms have been employed by many researchers for neural networks training with the different degree of success. Genetic Algorithms (GA) and Evolutionary Programming (EP) were used for weights and thresholds training [3,4], for search of efficient or minimal ANN structure and topology [5,6] and for optimization of learning algorithms themselves [7] The better results with GA were obtained in construction of optimal network structure, because ANN connectivity learning itself is considerably more difficult task for ....

D.B.Fogel, L.J.Fogel, W.W.Porto, Evolving Neural Networks, Biological Cybernetics, v.63, pp.487-493, 1990.

No context found.

D. B. Fogel, L. J. Fogel, and V. W. Porto. Evolving neural networks. Biological Cybernetics, 63:487--493, 1990.

No context found.

D. Fogel, L. Fogel, and V. Porto. Evolving Neural Networks. Biological Cybernetics, 63:487-493, 1990.

No context found.

D. B. Fogel, L. J. Fogel and V. W. Porto, "Evolving neural networks," Biological Cybernetics, 63, pp. 487-493, 1990.

No context found.

D. B. Fogel, L. J. Fogel, and V. W. Porto, "Evolving neural networks," Biological Cybernetics, vol. 63, pp. 487--493, 1990.

No context found.

Fogel D.B, Fogel L.J. & Porto V.W., Evolving neural networks. Biological Cybernetics, Vol. 63, 1990.

No context found.

Fogel D.B., Fogel L.J., and Porto V.W., (1990). Evolving Neural Networks, Biol. Cybern., vol. 63, pp.

No context found.

D. Fogel, L. Fogel and V. Porto (1990). Evolving neural networks. Biological Cybernetics, 63, pp. 487493.

No context found.

D.B. Fogel, L.J. Fogel, and V.W. Porto. Evolving Neural Networks. Biological Cybernetics, 63:487--493, 1990.

First 50 documents

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