Showing papers in "Neural Computing and Applications in 2004"
TL;DR: Empirical results indicate that HFM is relatively less accurate and RBFN is relatively more reliable for the weather forecasting problem, while the ensemble of neural networks produced the most accurate forecasts.
Abstract: This study presents the applicability of an ensemble of artificial neural networks (ANNs) and learning paradigms for weather forecasting in southern Saskatchewan, Canada. The proposed ensemble method for weather forecasting has advantages over other techniques like linear combination. Generally, the output of an ensemble is a weighted sum, which are weight-fixed, with the weights being determined from the training or validation data. In the proposed approach, weights are determined dynamically from the respective certainties of the network outputs. The more certain a network seems to be of its decision, the higher the weight. The proposed ensemble model performance is contrasted with multi-layered perceptron network (MLPN), Elman recurrent neural network (ERNN), radial basis function network (RBFN), Hopfield model (HFM) predictive models and regression techniques. The data of temperature, wind speed and relative humidity are used to train and test the different models. With each model, 24-h-ahead forecasts are made for the winter, spring, summer and fall seasons. Moreover, the performance and reliability of the seven models are then evaluated by a number of statistical measures. Among the direct approaches employed, empirical results indicate that HFM is relatively less accurate and RBFN is relatively more reliable for the weather forecasting problem. In comparison, the ensemble of neural networks produced the most accurate forecasts.
299 citations
TL;DR: A brief overview of feedforward ANNs and GAs is given followed by a review of the current state of research in applying evolutionary techniques to training RBF networks.
Abstract: The problems associated with training feedforward artificial neural networks (ANNs) such as the multilayer perceptron (MLP) network and radial basis function (RBF) network have been well documented. The solutions to these problems have inspired a considerable amount of research, one particular area being the application of evolutionary search algorithms such as the genetic algorithm (GA). To date, the vast majority of GA solutions have been aimed at the MLP network. This paper begins with a brief overview of feedforward ANNs and GAs followed by a review of the current state of research in applying evolutionary techniques to training RBF networks.
118 citations
TL;DR: The GA is incorporated to improve the learning and generalizability of ANNs for stock market prediction and shows that the performance of the proposed model is better than two conventional methods for artificial neural networks.
Abstract: This paper compares a feature transformation method using a genetic algorithm (GA) with two conventional methods for artificial neural networks (ANNs) In this study, the GA is incorporated to improve the learning and generalizability of ANNs for stock market prediction Daily predictions are conducted and prediction accuracy is measured In this study, three feature transformation methods for ANNs are compared Comparison of the results achieved by a feature transformation method using the GA to the other two feature transformation methods shows that the performance of the proposed model is better Experimental results show that the proposed approach reduces the dimensionality of the feature space and decreases irrelevant factors for stock market prediction
106 citations
TL;DR: A neural network auto regressive with exogenous input (NNARX) model is used to predict the indoor temperature of a residential building and shows that the NNARX model outperforms the linear model considerably.
Abstract: A neural network auto regressive with exogenous input (NNARX) model is used to predict the indoor temperature of a residential building. Firstly, the optimal regressor of a linear ARX model is identified by minimising Akaike’s final prediction error (FPE). This regressor is then used as the input vector of a fully connected feedforward neural network with one hidden layer of ten units and one output unit. Results show that the NNARX model outperforms the linear model considerably: the sum of the squared error (SSE) is 15.0479 with the ARX model and 2.0632 with the NNARX model. The optimal network topology is subsequently determined by pruning the fully connected network according to the optimal brain surgeon (OBS) strategy. With this procedure near 73% of connections were removed and, as a result, the performance of the network has been improved: the SSE is equal to 0.9060.
95 citations
TL;DR: The MNN method was applied to the problem of forecasting an hourly customer demand for gas at a compression station in Saskatchewan, Canada and showed that a MNN model performed better than a single ANN model for long term prediction.
Abstract: The artificial neural network (ANN) methodology has been used in various time series prediction applications. However, the accuracy of a neural network model may be seriously compromised when it is used recursively for making long-term multi-step predictions. This study presents a method using multiple ANNs to make a long term time series prediction. A multiple neural network (MNN) model is a group of neural networks that work together to solve a problem. In the proposed MNN approach, each component neural network makes forecasts at a different length of time ahead. The MNN method was applied to the problem of forecasting an hourly customer demand for gas at a compression station in Saskatchewan, Canada. The results showed that a MNN model performed better than a single ANN model for long term prediction.
73 citations
TL;DR: It is shown that the ANFIS architecture can model a nonlinear system very accurately by means of input–output pairs obtained either from the actual system or its mathematical model and it is also shown that such a system can be controlled effectively by a fuzzy controller.
Abstract: This paper aims to serve two main objectives; one is to demonstrate the modelling capabilities of a neuro-fuzzy approach, namely ANFIS (adaptive-network based fuzzy inference system) to a nonlinear system; and the other is to design a fuzzy controller to control such a system The nonlinear system, which is a liquid-level system, is represented first by its mathematical model and then by ANFIS architecture The ANFIS model is formed by means of input–output data set taken from the mathematical model Then a PID-type fuzzy controller, which linguistically approximates the classical three-term compensation, was designed to control the system represented by both its mathematical and ANFIS models in order to perform an agreement comparison between them It is shown that the ANFIS architecture can model a nonlinear system very accurately by means of input–output pairs obtained either from the actual system or its mathematical model It is also shown that such a system can be controlled effectively by a fuzzy controller
50 citations
TL;DR: A novel approach to the control of the cutting force on the basis of the internal model control (IMC) principle, based on artificial neural networks, demonstrates that IMC-NN strategy provides a better disturbance rejection than FLC for the cases analysed.
Abstract: This paper presents a novel approach to the control of the cutting force on the basis of the internal model control (IMC) principle. The main goal is to control a single output variable, the cutting force, by changing a single input variable, the feedrate. A neural model is used as an internal model to determine the control inputs (feedrate) necessary to keep the cutting force constant. Three approaches, the fuzzy logic controller (FLC), the direct inverse controller (DIC) and the IMC, based on artificial neural networks (IMC-NN), are simulated and their performances are assessed in terms of several performance measurements. The results demonstrate that IMC-NN strategy provides a better disturbance rejection than FLC for the cases analysed.
44 citations
TL;DR: This article applies both network techniques to predict the catches of the Prionace Glauca and the Katsowonus Pelamis, and shows that functional networks are more efficient than ANNs.
Abstract: In recent years, functional networks have emerged as an extension of artificial neural networks (ANNs). In this article, we apply both network techniques to predict the catches of the Prionace Glauca (a class of shark) and the Katsowonus Pelamis (a variety of tuna, more commonly known as the Skipjack). We have developed an application that will help reduce the search time for good fishing zones and thereby increase the fleet’s competitivity. Our results show that, thanks to their superior learning and generalisation capacities, functional networks are more efficient than ANNs. Our data proceeds from remote sensors. Their spectral signatures allow us to calculate products that are useful for ecological modelling. After an initial phase of digital image processing, we created a database that provides all the necessary patterns to train both network types.
37 citations
TL;DR: A support vector machine (SVM) classifier was trained to predict whether or not a surface residue is an interface residue, based on the identity of the target residue and its ten sequence neighbors, indicating that the method performs substantially better than chance (zero correlation).
Abstract: In this paper, we describe a machine learning approach for sequence-based prediction of protein-protein interaction sites. A support vector machine (SVM) classifier was trained to predict whether or not a surface residue is an interface residue (i.e., is located in the protein-protein interaction surface), based on the identity of the target residue and its ten sequence neighbors. Separate classifiers were trained on proteins from two categories of complexes, antibody-antigen and protease-inhibitor. The effectiveness of each classifier was evaluated using leave-one-out (jack-knife) cross-validation. Interface and non-interface residues were classified with relatively high sensitivity (82.3% and 78.5%) and specificity (81.0% and 77.6%) for proteins in the antigen-antibody and protease-inhibitor complexes, respectively. The correlation between predicted and actual labels was 0.430 and 0.462, indicating that the method performs substantially better than chance (zero correlation). Combined with recently developed methods for identification of surface residues from sequence information, this offers a promising approach to predict residues involved in protein-protein interactions from sequence information alone.
34 citations
TL;DR: A fault diagnosis procedure for analog linear circuits that uses an off-line trained neural network as a classifier and the way the information provided by testability and ambiguity group determination is exploited when choosing the neural network architecture is presented.
Abstract: A fault diagnosis procedure for analog linear circuits is presented. It uses an off-line trained neural network as a classifier. The innovative aspect of the proposed approach is the way the information provided by testability and ambiguity group determination is exploited when choosing the neural network architecture. The effectiveness of the proposed approach is shown by comparing with similar work that has already appeared in the literature.
32 citations
TL;DR: In this article, a method for on-line identification of non-linear systems is proposed based upon the optimisation methodology with Hopfield neural networks, which is adapted so that the weights of the resulting network are time-varying.
Abstract: In this work, a novel method for on-line identification of non-linear systems is proposed based upon the optimisation methodology with Hopfield neural networks. The original Hopfield model is adapted so that the weights of the resulting network are time-varying. A rigorous analytical study proves that, under mild assumptions, the estimations provided by the method converge to the actual parameter values in the case of constant parameters, or to a bounded neighbourhood of the parameters when these are time-varying. Time-varying parameters, often appearing in mechanical systems, are dealt with by the neural estimator in a more natural way than by least squares techniques. Both sudden and slow continuous variations are considered. Besides, in contrast to the gradient method, the neural estimator does not critically depend on the adjustment of the gain. The proposed method is applied to the identification of a robotic system with a flexible link. A reduced output prediction error and an accurate estimation of parameters are observed in simulation results.
TL;DR: A new algorithm for ranking the input features and obtaining the best feature subset is developed and illustrated in this paper and it is shown that even for noisy data, this algorithm still works well.
Abstract: A new algorithm for ranking the input features and obtaining the best feature subset is developed and illustrated in this paper. The asymptotic formula for mutual information and the expectation maximisation (EM) algorithm are used to developing the feature selection algorithm in this paper. We not only consider the dependence between the features and the class, but also measure the dependence among the features. Even for noisy data, this algorithm still works well. An empirical study is carried out in order to compare the proposed algorithm with the current existing algorithms. The proposed algorithm is illustrated by application to a variety of problems.
TL;DR: In this paper, the authors highlight the effect of the spread factor on the growing self-organising map and contrast this effect with grid size change (increase and decrease) in the SOM.
Abstract: The growing self-organising map (GSOM) has recently been proposed as an alternative neural network architecture based on the traditional self-organising map (SOM). The GSOM provides the user with the ability to control the spread of the map by defining a parameter called the spread factor (SF), which results in enhanced data mining and hierarchical clustering opportunities. When experimenting with the SOM, the grid size (number of rows and columns of nodes) can be changed until a suitable cluster distribution is achieved. In this paper we highlight the effect of the spread factor on the GSOM and contrast this effect with grid size change (increase and decrease) in the SOM. We also present experimental results in support of our claims regarding differences between GSOM and SOM.
TL;DR: A comparative study of DNNs, DFNs, and DWNs for non-linear dynamical system modeling and it is shown that all dynamic networks can be effectively used in non- linear system modeling, and that DWNs result in the best capacity.
Abstract: Intelligent systems cover a wide range of technologies related to hard sciences, such as modeling and control theory, and soft sciences, such as the artificial intelligence (AI). Intelligent systems, including neural networks (NNs), fuzzy logic (FL), and wavelet techniques, utilize the concepts of biological systems and human cognitive capabilities. These three systems have been recognized as a robust and attractive alternative to the some of the classical modeling and control methods. The application of classical NNs, FL, and wavelet technology to dynamic system modeling and control has been constrained by the non-dynamic nature of their popular architectures. The major drawbacks of these architectures are the curse of dimensionality, such as the requirement of too many parameters in NNs, the use of large rule bases in FL, the large number of wavelets, and the long training times, etc. These problems can be overcome with dynamic network structures, referred to as dynamic neural networks (DNNs), dynamic fuzzy networks (DFNs), and dynamic wavelet networks (DWNs), which have unconstrained connectivity and dynamic neural, fuzzy, and wavelet processing units, called “neurons”, “feurons”, and “wavelons”, respectively. The structure of dynamic networks are based on Hopfield networks. Here, we present a comparative study of DNNs, DFNs, and DWNs for non-linear dynamical system modeling. All three dynamic networks have a lag dynamic, an activation function, and interconnection weights. The network weights are adjusted using fast training (optimization) algorithms (quasi-Newton methods). Also, it has been shown that all dynamic networks can be effectively used in non-linear system modeling, and that DWNs result in the best capacity. But all networks have non-linearity properties in non-linear systems. In this study, all dynamic networks are considered as a non-linear optimization with dynamic equality constraints for non-linear system modeling. They encapsulate and generalize the target trajectories. The adjoint theory, whose computational complexity is significantly less than the direct method, has been used in the training of the networks. The updating of weights (identification of network parameters) is based on Broyden–Fletcher–Goldfarb–Shanno method. First, phase portrait examples are given. From this, it has been shown that they have oscillatory and chaotic properties. A dynamical system with discrete events is modeled using the above network structure. There is a localization property at discrete event instants for time and frequency in this example.
TL;DR: A new hybrid model for time-series forecasting which combines ANNs with genetic algorithms (GAs) is presented, which allows the inclusion of exogenous information (EI) without additional pre-processing.
Abstract: In this paper, we present a new model for time-series forecasting using radial basis functions (RBFs) as a unit of artificial neural networks (ANNs), which allows the inclusion of exogenous information (EI) without additional pre-processing We begin by summarizing the most well-known EI techniques used ad hoc, ie, principal component analysis (PCA) and independent component analysis (ICA) We analyze the advantages and disadvantages of these techniques in time-series forecasting using Spanish bank and company stocks Then, we describe a new hybrid model for time-series forecasting which combines ANNs with genetic algorithms (GAs) We also describe the possibilities when implementing the model on parallel processing systems
TL;DR: A combination of multiple neural networks is selected and used to model nonlinear multi-input multi-output (MIMO) processes with time delays and an optimisation procedure for a nonlinear model-predictive control (MPC) algorithm is developed.
Abstract: A combination of multiple neural networks (NNs) is selected and used to model nonlinear multi-input multi-output (MIMO) processes with time delays. An optimisation procedure for a nonlinear model-predictive control (MPC) algorithm based on this model is then developed. The proposed scheme has been applied and evaluated for two example problems, including the MPC of a multi-component distillation column.
TL;DR: This work presents a novel RF framework that learns one-class support vector machines (1SVM) from retrieval experience to represent the set memberships of users’ high-level concepts and stores them in a “concept database”.
Abstract: Relevance feedback (RF) is an iterative process which improves the performance of content-based image retrieval by modifying the query and similarity metric based on the user’s feedback on the retrieval results. This short-term learning within a single query session is called intra-query learning. However, the interaction history of previous users over all past queries may also be potentially exploited to help improve the retrieval performance for the current query. The long-term learning accumulated over the course of many query sessions is called inter-query learning. We present a novel RF framework that learns one-class support vector machines (1SVM) from retrieval experience to represent the set memberships of users’ high-level concepts and stores them in a “concept database”. The “concept database” provides a mechanism for accumulating inter-query learning obtained from previous queries. By doing a fuzzy classification of a query into the regions of support represented by the 1SVMs, past experience is merged with current intra-query learning. The geometric view of 1SVM allows a straightforward interpretation of the density of past interaction in a local area of the feature space and thus allows the decision of exploiting past information only if enough past exploration of the local area has occurred. The proposed approach is evaluated on real data sets and compared against both traditional intra-query-learning-only RF approaches and other methods that also exploit inter-query learning.
TL;DR: It was found that functions other than the commonly used sigmoidal function could perform well when used as hidden layer transfer functions, and three of the four problems showed improved test results when these evolved functions were used.
Abstract: The paper describes a methodology for constructing transfer functions for the hidden layer of a back-propagation network, which is based on evolutionary programming. The method allows the construction of almost any mathematical form. It is tested using four benchmark classification problems from the well-known machine intelligence problems repository maintained by the University of California, Irvine. It was found that functions other than the commonly used sigmoidal function could perform well when used as hidden layer transfer functions. Three of the four problems showed improved test results when these evolved functions were used.
TL;DR: The developed cluster-based combinatorial forecasting schemes were examined in a single-step ahead prediction of the pound-dollar daily exchange rate and demonstrated an improvement over conventional linear and neural based combinatorially schemes.
Abstract: Time series analysis utilising more than a single forecasting approach is a procedure originated many years ago as an attempt to improve the performance of the individual model forecasts. In the literature there is a wide range of different approaches but their success depends on the forecasting performance of the individual schemes. A clustering algorithm is often employed to distinguish smaller sets of data that share common properties. The application of clustering algorithms in combinatorial forecasting is discussed with an emphasis placed on the formulation of the problem so that better forecasts are generated. Additionally, the hybrid clustering algorithm that assigns data depending on their distance from the hyper-plane that provides their optimal modelling is applied. The developed cluster-based combinatorial forecasting schemes were examined in a single-step ahead prediction of the pound-dollar daily exchange rate and demonstrated an improvement over conventional linear and neural based combinatorial schemes.
TL;DR: The main characteristics of the AUDyC and its abilities to model on-line non-stationary data are presented and some experimental results stemmed from a supervision application of a hydraulic system are discussed.
Abstract: A new supervision system consisting of three modules is presented. The main novelty is the first module that corresponds to a modelling task. This module, which uses the auto-adaptive and dynamical clustering (AUDyC) neural network, allows us to continuously analyse and classify the functioning state of the monitored system using a dynamical modelling of all known modes (good/bad functioning modes represent different classes). The second module exploits these models of the functioning modes in order to detect “fast” and “slow” deviations. From membership degrees and from the information extracted by the monitoring module, the third module, dedicated to the diagnostics, informs the user about the functioning conditions of the system. In this paper, the main characteristics of the AUDyC and its abilities to model on-line non-stationary data are presented. Then, the description of the supervision system is given and some experimental results stemmed from a supervision application of a hydraulic system are discussed.
TL;DR: A loss function putting in balance the smoothed fitting induced by the noise injection and the precision of approximation, is proposed, which can be derived in general for parametrical models that satisfy the Lipschitz property.
Abstract: Injecting input noise during feedforward neural network (NN) training can improve generalization performance markedly. Reported works justify this fact arguing that noise injection is equivalent to a smoothing regularization with the input noise variance playing the role of the regularization parameter. The success of this approach depends on the appropriate choice of the input noise variance. However, it is often not known a priori if the degree of smoothness imposed on the FNN mapping is consistent with the unknown function to be approximated. In order to have a better control over this smoothing effect, a loss function putting in balance the smoothed fitting induced by the noise injection and the precision of approximation, is proposed. The second term, which aims at penalizing the undesirable effect of input noise injection or controlling the deviation of the random perturbed loss, was obtained by expressing a certain distance between the original loss function and its random perturbed version. In fact, this term can be derived in general for parametrical models that satisfy the Lipschitz property. An example is included to illustrate the effectiveness of learning with this proposed loss function when noise injection is used.
TL;DR: A novel approach combining the techniques of independent component analysis (ICA) and dynamical embedding is presented, which can be used to extract and isolate components of interest from single-channel unaveraged MEG data.
Abstract: A method for the decomposition of single-channel unaveraged magnetoencephalographic (MEG) data into statistically independent components is presented. The study of MEG recordings is characterised by a host of difficulties, most of which stem from the inherently noisy recording process by which the data is obtained. MEG time series typically contain a mix of artifactual components from a variety of sources, and the isolation of interesting signals from this noise background poses a difficult problem. In this article, we present a novel approach combining the techniques of independent component analysis (ICA) and dynamical embedding, which can be used to extract and isolate components of interest from single-channel unaveraged MEG data. In our approach, the method of delays is proposed as a means of augmenting the single-channel data, thus, facilitating the application of ICA. Finally, because the single-channel approach yields no information regarding the physiological origins of extracted sources, we discuss a method by which extracted sources may be projected back into the multichannel measurement space, permitting an estimate of the respective spatial distributions to be obtained. The proposed methods are tested on three separate MEG channels and the results are presented and discussed.
TL;DR: The model presented herein develops a disaggregated accelerator equation whose coefficients are the weights of a Kohonen neural net that represents firms’ decision-making that takes place when managers recognise emerging technological patterns.
Abstract: The investment acceleration principle is a heuristic for modelling a investment time series out of a consumption time series. The model presented herein develops a disaggregated accelerator equation whose coefficients are the weights of a Kohonen neural net that represents firms’ decision-making. According to this model, investments take place when managers recognise emerging technological patterns. Furthermore, a technique borrowed from the theory of self-organising systems is used in order to disentangle innovation-driven investments from plant-replication investments.
TL;DR: An information system that classifies Web pages according a taxonomy, which is mainly used from seven search engines/directories, is proposed that aims to perform the information segmentation according to information filtering techniques using content descriptor vectors.
Abstract: This paper proposes an information system that classifies Web pages according a taxonomy, which is mainly used from seven search engines/directories. The proposed classifier is a four-layer generalised regression neural network (GRNN) that aims to perform the information segmentation according to information filtering techniques using content descriptor vectors. Eight categories of Web pages were used in order to evaluate the robustness of the method, while no restrictions were imposed except for the language of the content, which is English. The system can be used as an assistant and consultative tool for classification purposes as well as for estimating the population of Web pages at any given point in time.
TL;DR: This paper compares the search space for four different types of ANN architecture for controller evolution through an information-theoretic analysis of the fitness landscape associated with each type of architecture.
Abstract: Recently, there has been a lot of interest in evolving controllers for both physically simulated creatures as well as for real physical robots. However, a range of different ANN architectures are used for controller evolution, and, in the majority of the work conducted, the choice of the architecture used is made arbitrarily. No fitness landscape analysis was provided for the underlying fitness landscape of the controller’s search space. As such, the literature remains largely inconclusive as to which ANN architecture provides the most efficient and effective space for searching the range of possible controllers through evolutionary methods. This represents the motivation for this paper where we compare the search space for four different types of ANN architecture for controller evolution through an information-theoretic analysis of the fitness landscape associated with each type of architecture.
TL;DR: The backpropagation neural network (BNN) and Karhunen-Loeve expansion method is used to construct a new and highly accurate grading system and demonstrates that as the input dimensions are reduced to four in a self-healing neural network with the K-L expansion, the grading system provides the high accuracy and robustness.
Abstract: The grade of textile yarns is an important index in evaluating the yarn’s market value. This paper uses the backpropagation neural network (BNN) and Karhunen-Loeve (K-L) expansion method to construct a new and highly accurate grading system. Outcomes show that a highly accurate and neutral grading system can be obtained if the BNN learning sample is comprehensive or by adopting the BNN with a relearning technique (self-healing). Considering the possibility of reducing the dimension of BNN input vectors without losing the accuracy, this paper preprocesses the BNN grading system using the K-L expansion. Experiments demonstrate that the K-L expansion provides a way to reduce the input dimensions, and that a single principle axis value of the BNN with the K-L expansion grading system is able to grade textile yarns. In addition, the experiment demonstrates that as the input dimensions are reduced to four in a self-healing neural network with the K-L expansion, the grading system provides the high accuracy and robustness.
TL;DR: A content-based self-organizing approach to multilingual information filtering using fuzzy logic and the self- Organizing map is proposed, which screens and evaluates multilingual documents based on their semantic contents.
Abstract: Effective multilingual information filtering is required to alleviate users’ burden of information overload resulting from the increasing flood of multilingual textual content available extensively over the World-Wide Web. This paper proposes a content-based self-organizing approach to multilingual information filtering using fuzzy logic and the self-organizing map. This approach screens and evaluates multilingual documents based on their semantic contents. Correlated multilingual documents are disseminated according to their corresponding themes or topics, thus enabling language-independent content-based information access efficiently and effectively. A Web-based multilingual online news-filtering system is developed to illustrate how the approach works.
Journal Article•
TL;DR: A pursuit system that utilizes the artificial life concept where autonomous mobile agents emulate the social behavior of animals and insects and realize their group behavior and the validity of the system is verified through simulation.
Abstract: This paper proposes a pursuit system that utilizes the artificial life concept where autonomous mobile agents emulate the social behavior of animals and insects and realize their group behavior. Each agent contains sensors to perceive other agents in several directions, and decides its behavior based on the information obtained by these sensors. In this paper, a neural network is used for behavior decision controlling. The input of the neural network is decided by the existence of other agents, and the distance to the other agents. The output determines the directions in which the agent moves. The connection weight values of this neural network are encoded as genes, and the fitness individuals are determined using a genetic algorithm. Here, the fitness values imply how much group behavior adequately fit the goal and can express group behavior. The validity of the system is verified through simulation. Also in this paper, we have observed the agents’ emergent behavior during simulation.
TL;DR: It is suggested that implementing GA with NN is a promising research direction for greatly reducing the running time of GA.
Abstract: This paper proposes using neural networks (NN) to implement a real coded genetic algorithm (GA) with the center of gravity crossover (CGX) and the minimal generation gap (MGG) model. With all genetic operations of GA including selection, crossover, mutation and evaluation implemented with NN modules, this approach can realize in parallel genetic operations on the whole chromosome to achieve the maximum parallel realization potential of the MGG model of the GA. At the same time expensive hardware for field programmable gate arrays (FPGA) and the high speed memory of hardware for GA can be avoided. The performance of our solution is validated with a suite of benchmark test functions. This paper suggests that implementing GA with NN is a promising research direction for greatly reducing the running time of GA.