By Topic

Combinations of Evolutionary Computation and Neural Networks, 2000 IEEE Symposium on

Date 11-13 May 2000

Filter Results

Displaying Results 1 - 25 of 31
  • 2000 IEEE Symposium On Combinations Of Evolutionary Computation And Neural N.etworks

    Publication Year: 2000, Page(s):0_3 - 0_8
    Request permission for commercial reuse | PDF file iconPDF (183 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 2000, Page(s): 250
    Request permission for commercial reuse | PDF file iconPDF (38 KB)
    Freely Available from IEEE
  • Evolution of recurrent cascade correlation networks with distributed collaborative species

    Publication Year: 2000, Page(s):240 - 249
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (700 KB)

    The vast research and experimental work of using EANN to evolve neural networks had achieved many successes, yet it also revealed some limitations. Aiming at boosting the EANN speed, improving its performance, the approach of Cooperative Co-evolution is introduced. Instead of one evolutionary algorithm that attempts to solve the whole problem, species representing simpler subtasks are evolved as s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convergence analysis of a segmentation algorithm for the evolutionary training of neural networks

    Publication Year: 2000, Page(s):70 - 81
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (876 KB)

    In contrast to standard genetic algorithms with generational reproduction, we adopt the viewpoint of the reactor algorithm (Dittrich and Banzhaf, 1998) which is similar to steady-state genetic algorithms, but without ranking. This permits an analysis similar to Eigen's (1971) molecular evolution model. From this viewpoint, we consider combining segments from different populations into one genotype... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simple evolving connectionist systems and experiments on isolated phoneme recognition

    Publication Year: 2000, Page(s):232 - 239
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (556 KB)

    Evolving connectionist systems (ECoS) are systems that evolve their structure through online, adaptive learning from incoming data. This paradigm complements the paradigm of evolutionary computation based on population based search and optimisation of individual systems through generations of populations. The paper presents the theory and architecture of a simple evolving system called SECoS that ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human magnetocardiogram (MCG) modeling using evolutionary artificial neural networks

    Publication Year: 2000, Page(s):110 - 120
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB)

    In the present work magnetocardiogram (MCG) recordings of normal subjects were analyzed using a hybrid training algorithm. This algorithm combines genetic algorithms and a training method based on the localized Extended Kalman Filter (EKF), in order to evolve the structure and train Multi-Layered Perceptrons (MLP) networks. Our goal is to examine the predictability of the MCG signal on a short pre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the use of biologically-inspired adaptive mutations to evolve artificial neural network structures

    Publication Year: 2000, Page(s):24 - 32
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (560 KB)

    Evolutionary algorithms have been used to successfully evolve artificial neural network structures. Normally the evolutionary algorithm has several different mutation operators available to randomly change the number and location of neurons or connections. The scope of any mutation is typically limited by a user-selected parameter. Nature, however, controls the total number of neurons and synaptic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neuro-evolution and natural deduction

    Publication Year: 2000, Page(s):64 - 69
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (456 KB)

    Natural deduction is essentially a sequential decision task, similar to many game-playing tasks. Such a task is well suited to benefit from the techniques of neuro-evolution. Symbiotic Adaptive Neuro-Evolution (SANE) (Moriarty and Miikkulainen, 1996) has proven successful at evolving networks for such tasks. This paper shows that SANE can be used to evolve a natural deduction system on a neural ne... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Specifying intrinsically adaptive architectures

    Publication Year: 2000, Page(s):224 - 231
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (516 KB)

    The paper describes a method for specifying (and evolving) intrinsically adaptive neural architectures. These architectures have back-propagation style gradient descent behavior built into them at a cellular level. The significance of this is that we can now use back-propagation to train evolved feedforward networks of any structure (provided that individual nodes are differentiable). Networks evo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimization for problem classes-neural networks that learn to learn

    Publication Year: 2000, Page(s):98 - 109
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1156 KB)

    The main focus of the optimization of artificial neural networks has been the design of a problem dependent network structure in order to reduce the model complexity and to minimize the model error. Driven by a concrete application we identify in this paper another desirable property of neural networks-the ability of the network to efficiently solve related problems denoted as a class of problems.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolving neural trees for time series prediction using Bayesian evolutionary algorithms

    Publication Year: 2000, Page(s):17 - 23
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (512 KB)

    Bayesian evolutionary algorithms (BEAs) are a probabilistic model for evolutionary computation. Instead of simply generating new populations as in conventional evolutionary algorithms, the BEAs attempt to explicitly estimate the posterior distribution of the individuals from their prior probability and likelihood, and then sample offspring from the distribution. We apply the Bayesian evolutionary ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An adaptive scheme for real function optimization acting as a selection operator

    Publication Year: 2000, Page(s):140 - 149
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (640 KB)

    We propose an adaptive scheme for real function optimization whose dynamics is driven by selection. The method is parametric and relies explicitly on the Gaussian density seen as an infinite search population. We define two gradient flows acting on the density parameters, in the spirit of neural network learning rules, which maximize either the function expectation relatively to the density or its... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolution and design of distributed learning rules

    Publication Year: 2000, Page(s):59 - 63
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB)

    The paper describes the application of neural networks as learning rules for the training of neural networks. The learning rule is part of the neural network architecture. As a result the learning rule is non-local and globally distributed within the network. The learning rules are evolved using an evolution strategy. The survival of a learning rule is based on its performance in training neural n... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic modelling and time-series prediction by incremental growth of lateral delay neural networks

    Publication Year: 2000, Page(s):216 - 223
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (612 KB)

    The difficult problems of predicting chaotic time series and modelling chaotic systems is approached using an innovative neural network design. By combining evolutionary techniques with others, good results can be obtained swiftly via incremental network growing. The network architecture and training algorithm make the creation of dynamic models efficient and hassle-free. The network results accur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Case studies in applying fitness distributions in evolutionary algorithms. II. Comparing the improvements from crossover and Gaussian mutation on simple neural networks

    Publication Year: 2000, Page(s):91 - 97
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (436 KB)

    Previous efforts in applying fitness distributions of Gaussian mutation for optimizing simple neural networks in the XOR problem are extended by conducting a similar analysis for three types of crossover operators. One-point, two-point and uniform crossover are applied to the best-evolved neural networks at each generation in an evolutionary trial. The maximum expected improvement under Gaussian m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploring different coding schemes for the evolution of an artificial insect eye

    Publication Year: 2000, Page(s):10 - 16
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (660 KB)

    The existing literature proposes various (neuronal) architectures for object avoidance, which is one of the very fundamental tasks of autonomous, mobile robots. Due to certain hardware limitations, existing research resorts to prespecified sensor systems that remain fixed during all experiments, and modifications are done only in the controllers' software components. Only recent research (Lichtens... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extracting comprehensible rules from neural networks via genetic algorithms

    Publication Year: 2000, Page(s):130 - 139
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (848 KB)

    A common problem in KDD (Knowledge Discovery in Databases) is the presence of noise in the data being mined. Neural networks are robust and have a good tolerance to noise, which makes them suitable for mining very noisy data. However, they have the well-known disadvantage of not discovering any high-level rule that can be used as a support for human decision making. In this work we present a metho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolving neural networks using attribute grammars

    Publication Year: 2000, Page(s):37 - 42
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (460 KB)

    The evolutionary optimization of neural networks involves two main design issues: how the neural network is represented genetically, and how that representation is manipulated through genetic operations. We have developed a genetic representation that uses an attribute grammar to encode both topological and architectural information about a neural network. We have defined genetic operators that ar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inductive genetic programming of polynomial learning networks

    Publication Year: 2000, Page(s):158 - 167
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (756 KB)

    Learning networks have been empirically proven suitable for function approximation and regression. Our concern is finding well performing polynomial learning networks by inductive Genetic Programming (iGP). The proposed iGP system evolves tree-structured networks of simple transfer polynomials in the hidden units. It discovers the relevant network topology for the task, and rapidly computes the ne... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new metric for evaluating genetic optimization of neural networks

    Publication Year: 2000, Page(s):52 - 58
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (648 KB)

    In recent years researchers have used genetic algorithm techniques to evolve neural network topologies. Although these researchers have had the same end result in mind (namely, the evolution of topologies that are better able to solve a particular problem), the approaches they used varied greatly. Random selection of a genome coding scheme can easily result in sub-optimal genetic performance, sinc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Multi-Tiered Tournament Selection for evolutionary neural network synthesis

    Publication Year: 2000, Page(s):207 - 215
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    The paper introduces Multi-Tiered Tournament Selection. Traditional tournament selection algorithms are appropriate for single objective optimization problems but are too limited for the multi-objective task of evolving complete recognition systems. Recognition systems need to be accurate as well as small to improve generalization performance. Multi-tiered Tournament Selection is shown to improve ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Artificial neural development for pulsed neural network design-a simulation experiment on animat's cognitive map genesis

    Publication Year: 2000, Page(s):188 - 198
    Cited by:  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (948 KB)

    We propose the artificial neural development method that generates the three-dimensional multi-regional pulsed neural network arranged in three layers of the nerve area layer, the nerve sub-area layer, and the cell layer. In this method, the neural development process consists of the first genome-controlled spatiotemporal generation of a neural network structure and the latter spiking activity-dep... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network structures and isomorphisms: random walk characteristics of the search space

    Publication Year: 2000, Page(s):82 - 90
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (732 KB)

    We deal with a quite general topic in evolutionary structure optimization, namely redundancy in the encoding due to isomorphic structures. This problem is well known in topology optimization of neural networks (NNs). In the context of structure optimization of NNs we observe similar phenomena of rare and frequent structures as are known from molecular biology. The degree to which isomorphic struct... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computation: evolutionary, neural, molecular

    Publication Year: 2000, Page(s):1 - 9
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (900 KB)

    A confluence of factors emanating from computer science, biology, and technology have brought self-organizing approaches back to the fore. Neural networks in particular provide high evolvability platforms for variation-selection search strategies. The neuron doctrine and the fundamental nature of computing come into question. Is a neuron an atom of the brain or is it itself a complex information p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining incrementally evolved neural networks based on cellular automata for complex adaptive behaviors

    Publication Year: 2000, Page(s):121 - 129
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (856 KB)

    There has been extensive work to construct an optimal controller for a mobile robot by evolutionary approaches such as genetic algorithm, genetic programming, and so on. However, evolutionary approaches have a difficulty to obtain the controller for complex and general behaviors. In order to overcome this shortcoming, we propose an incremental evolution method for neural networks based on cellular... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.