R. Salomon. Evolutionary algorithms and gradient search: Similarities and di#erences. IEEE Transactions on Evolutionary Computation, 2(2):45--55, 1998. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Balance between Genetic Search and Local Search in.. - Ishibuchi, Yoshida.. (2002) (1 citation) (Correct)
....A in Fig. 11 will move to the first examined neighbor among C, D and E. It should be noted that the local search direction specified by the weight vector w in the objective space is a totally different concept from the local search direction in the continuous decision space (e.g. see Salomon [44]) Fig. 12 Pseudo weight vector. In the calculation of the pseudo weight vector for each solution, we need the maximum and minimum values of each objective over the current population. Thus this approach has some computational overhead. The overhead, however, is not large because the ....
R. Salomon, "Evolutionary algorithms and gradient search: Similarities and differences," IEEE Trans. on Evolutionary Computation, vol. 2, no. 2, pp. 45-55, July 1998.
An Adaptive Scheme for Real Function Optimization Acting as a.. - Berny (2000) (Correct)
....q (x) m) 6) The effect of system (6) is to make m closer to the mean of the selected population. If we introduce the operator L defined by L(f) x) Z (f(z) f(x) z x) p(dz) we can write system (6) as dm dt = C (Lf) m) which is at the core of the evolutionary algorithm presented in [Sal98], up to the matrix C since the author assumes a normal Gaussian density with identity covariance matrix. Using the variable z = T 1 (x) in the normal space, we further simplify system (6) and obtain dm dt = M E q (z) 7) Apart from the expectation operator, dm=dt can be calculated in a time ....
R. Salomon. Evolutionary algorithms and gradient search: similarities and differences. IEEE Transactions on Evolutionary Computation, 2(2):45--55, July 1998.
Algorithms and Architectures for use with Nanoelectronic.. - Forshaw (1999) (Correct)
....to have poor dynamic error statistics, it seems likely that FPGAs will not be a useful option in the long term. One should also note that, although genetic algorithms are very powerful within their own range of applications [17] outside this range they exhibit quite rapid fall off in efficiency [57]. Once trained, neural networks are often hard to interpret, in the sense that the patterns of weights and connections which they have developed during training are usually not simple mappings of what they have learned to recognise. To give an extreme example, it is possible for researchers to ....
R. Salomon, "Evolutionary Algorithms and Gradient Search: Similarities and Differences", IEEE Tran. Evol. Comput. 2, 45-55, 1998.
Performance and Efficiency: Recent Advances in Supervised Learning - Ji, Ma (1999) (1 citation) (Correct)
....we focus on specific applications of evolutionary algorithms to tackling the issues of training neural networks. Other applications can be found in [41] which include applying evolutionary algorithms to finding appropriate network architecture [105] 73] and adaptively adjusting the learning rate [92]. We first illustrate how to apply evolutionary algorithms to train a neural network. We then discuss the similarities and differences between evolutionary algorithms and the algorithm for combinations of weak perceptrons. 7.1 Evolutionary Computation A fundamental difficulty of using a ....
R. Salomon. Evolutionary algorithms and gradient search: Similarities and differences. IEEE Transactions on Evolutionary Computation, 2:45 -- 55, 1998.
Applying Evolutionary Algorithms to Real-World-Inspired Problems.. - Salomon (1999) Self-citation (Salomon) (Correct)
.... such as Rastrigin s function f rastrigin ( x) P i [x 2 i 10 cos(2 x i ) 10] and Schwefel s function f schwefel ( x) P i x i sin( p jx i j) For these (standard) test functions, the pertinent literature on evolutionary algorithms provides a large amount of experimental data [7, 5, 6, 11, 12] as well as theoretical analyses [2, 3, 4, 10] In the evaluation of evolutionary algorithms, surprisingly little attention has been devoted to relatively simple functions, except the sphere. It is interesting to note that in the early days, Rechenberg and Schwefel [8, 13] have applied various ....
Salomon, R., 1998. Evolutionary Algorithms and Gradient Search: Similarities and Differences. IEEE Transactions on Evolutionary Computation 2(2):45-55.
Evolution Strategies with Cumulative Step Length Adaptation on .. - Arnold, Beyer (2006) (Correct)
No context found.
R. Salomon. Evolutionary algorithms and gradient search: Similarities and di#erences. IEEE Transactions on Evolutionary Computation, 2(2):45--55, 1998.
Competent Memetic Algorithms: Model, Taxonomy and Dessing Issues - Krasnogor, Smith (Correct)
No context found.
R. Salomon, "Evolutionary algorithms and gradient search: Similarities and differences," IEEE Transactions On Evolutionary Computation, vol. 2(2), July 1998.
Evolving Neural Network Architecture and Weights - Using An Evolutionary (Correct)
No context found.
Ralf Salomon. Evolutionary algorithms and gradient search: Similarities and di#erences. IEEE Transactions on Evolutionary Computation, 2(2):45--55, 1998.
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