Node Level Crossover Applied to Neural Network Evolution

@inproceedings{SanzTapia2003NodeLC,
  title={Node Level Crossover Applied to Neural Network Evolution},
  author={Eloy Sanz-Tapia and Nicol{\'a}s Garc{\'i}a-Pedrajas and Domingo Ortiz-Boyer and C{\'e}sar Herv{\'a}s‐Mart{\'i}nez},
  booktitle={IWANN},
  year={2003}
}
This work presents an analysis of the convergence behaviour of the Univariate Marginal Distribution Algorithm (UMDA) when it is used to maximize a number of pseudo-boolean functions. The analysis is based on modeling the algorithm using a reducible Markov chain, whose absorbing states correspond to the individuals of the search space. The absorption probability to the optimum and the expected time of convergence to the set of absorbing states are calculated for each function. This… 

References

SHOWING 1-10 OF 21 REFERENCES
An evolutionary algorithm that constructs recurrent neural networks
TLDR
It is argued that genetic algorithms are inappropriate for network acquisition and an evolutionary program is described, called GNARL, that simultaneously acquires both the structure and weights for recurrent networks.
Non-redundant genetic coding of neural networks
  • D. Thierens
  • Computer Science
    Proceedings of IEEE International Conference on Evolutionary Computation
  • 1996
TLDR
A neural network genotype representation that completely eliminates the functional redundancies by transforming each neural network into its canonical form is discussed, which is computationally extremely simple.
Parallel Problem Solving from Nature — PPSN VII
TLDR
With relatively little effort, scaling laws that quite accurately describe the behavior of the strategy and that greatly contribute to its understanding are derived and their implications are discussed.
Combinatonal Optimization by Learning and Simulation of Bayesian Networks
This paper shows how the Bayesian network paradigm can be used in order to solve combinatorial optimization problems. To do it some methods of structure learning from data and simulation of Bayesian
Theoretical Analysis of the Confidence Interval Based Crossover for Real-Coded Genetic Algorithms
TLDR
The mean and variance of the population when this crossover operator is applied is analyzed, studying the behavior of the distribution of the fitness of the individuals in a problem of optimization.
From Recombination of Genes to the Estimation of Distributions I. Binary Parameters
TLDR
The problem is the problem and several modifications of sexual recombination are investigated, which leads to marginal distribution algorithms, which lead to more sophisticated methods, based on estimating the distribution of promising points.
Evolving artificial neural networks
  • X. Yao
  • Computer Science
    Proc. IEEE
  • 1999
TLDR
It is shown, through a considerably large literature review, that combinations between ANNs and EAs can lead to significantly better intelligent systems than relying on ANNs or EAs alone.
Crossover Operator Effect in Function Optimization with Constraints
TLDR
This work makes an analysis of the influence of the selection of the crossover operator in the problem of function optimization with constraints, and focuses on this operator because this operator is the most characteristic of genetic algorithms.
Forming Neural Networks Through Efficient and Adaptive Coevolution
TLDR
The symbiotic adaptive neuroevolution system coevolves a population of neurons that cooperate to form a functioning neural network to be more efficient and more adaptive and to maintain higher levels of diversity than the more common network-based population approaches.
Genetic Algorithms and Walsh Functions: Part I, A Gentle Introduction
TLDR
Bethke's Walshschema transform through the Walsh polynomials is introduced, which provides an intuitive basis for visualizing the nonlinearities being considered, thereby permitting the consideration of a number of useful extensions to the theory in Part II.
...
...