Neural network ensemble is a learning paradigm where many neural networks are jointly used to solve a problem. In this paper, the relationship between the ensemble and its component neural networks is analyzed from the context of both regression and classification, which reveals that it may be better to ensemble many instead of all of the neural networks at hand. This result is interesting because at present, most approaches ensemble all the available neural networks for prediction. Then, in order to show that the appropriate neural networks for composing an ensemble can be effectively selected from a set of available neural networks, an approach named GASEN is presented. GASEN trains a number of neural networks at first. Then it assigns random weights to those networks and employs genetic algorithm to evolve the weights so that they can characterize to some extent the fitness of the neural networks in constituting an ensemble. Finally it selects some neural networks based on the evolved weights to make up the ensemble. A large empirical study shows that, comparing with some popular ensemble approaches such as Bagging and Boosting, GASEN can generate neural network ensembles with far smaller sizes but stronger generalization ability. Furthermore, in order to understand the working mechanism of GASEN, the bias-variance decomposition of the error is provided in this paper, which shows that the success of GASEN may lie in that it can significantly reduce the bias as well as the variance.

An artificial neural network ensemble is a learning paradigm where several artificial neural networks are jointly used to solve a problem. In this paper, an automatic pathological diagnosis procedure named Neural Ensemble based Detection (NED) is proposed, which utilizes an artificial neural network ensemble to identify lung cancer cells in the images of the specimens of needle biopsies obtained from the bodies of the subjects to be diagnosed. The ensemble is built on a two-level ensemble architecture. The first-level ensemble is used to judge whether a cell is normal with high confidence where each individual network has only two outputs respectively normal cell or cancer cell. The predictions of those individual networks are combined by a novel method presented in this paper, i.e. full voting which judges a cell to be normal only when all the individual networks judge it is normal. The second-level ensemble is used to deal with the cells that are judged as cancer cells by the first-level ensemble, where each individual network has five outputs respectively adenocarcinoma, squamous cell carcinoma, small cell carcinoma, large cell carcinoma, and normal, among which the former four are different types of lung cancer cells. The predictions of those individual networks are combined by a prevailing method, i.e. plurality voting. Through adopting those techniques, NED achieves not only a high rate of overall identification but also a low rate of false negative identification, i.e. a low rate of judging cancer cells to be normal ones, which is important in saving lives due to reducing missing diagnoses of cancer patients.

We present an algorithm for automatic image orientation estimation using a Bayesian learning framework. We demonstrate that a small codebook (the optimal size of codebook is selected using a modified MDL criterion) extracted from a vector quantizer can be used to estimate the class-conditional densities of the observed features needed for the Bayesian methodology. We further show how feature clustering can be used as a feature selection mechanism to remove redundancies in the highdimensional feature vectors used for classification. Experiments on a database of 17; 901 images have shown that our proposed algorithm achieves an accuracy of approximately 97% on the training set and over 89% on an independent test set. 1. Introduction Content-based image organization and retrieval has emerged as an important area in computer vision and multimedia computing, due to the technological advances in digital imaging, storage, and networking. With the development of digital photography as well as...

Comprehensibility is very important for a machine learning technique to be used in computer-aided medical diagnosis. Since an artificial neural network ensemble is composed of multiple artificial neural networks, its comprehensibility is worse than that of a single artificial neural network. In this paper, C4.5 Rule-PANE which combines artificial neural network ensemble with rule induction by regarding the former as a pre-process of the latter, is proposed. At first, an artificial neural network ensemble is trained. Then, a new training data set is generated by feeding the feature vectors of the original training instances to the trained ensemble and replacing the expected class labels of the original training instances with the class labels output from the ensemble. Additional training data may also be appended by randomly generating feature vectors and combining them with their corresponding class labels output from the ensemble. Finally, a specific rule induction approach, i.e. C4.5 Rule, is used to learn rules from the new training data set. Case studies on diabetes, hepatitis, and breast cancer show that C4.5 Rule-PANE could generate rules with strong generalization ability, which profits from artificial neural network ensemble, and strong comprehensibility, which profits from rule induction.

Neural network ensemble is a learning paradigm where several neural networks are jointly used to solve a problem. In this paper, the relationship between the generalization ability of the neural network ensemble and the correlation of the individual neural networks is analyzed, which reveals that ensembling a selective subset of individual networks is superior to ensembling all the individual networks in some cases. Therefore an approach named GASEN is proposed, which trains several individual neural networks and then employs genetic algorithm to select an optimum subset of individual networks to constitute an ensemble. Experimental results show that, comparing with a popular ensemble approach, i.e. averaging all, and a theoretically optimum selective ensemble approach, i.e. enumerating, GASEN has preferable performance in generating ensembles with strong generalization ability in relatively small computational cost. 1

Neural network ensemble can significantly improve the generalization ability of neural network based systems. However, its comprehensibility is even worse than that of a single neural network because it comprises a collection of individual neural networks. In this paper, an approach named REFNE is proposed to improve the comprehensibility of trained neural network ensembles that perform classification tasks. REFNE utilizes the trained ensembles to generate instances and then extracts symbolic rules from those instances. It gracefully breaks the ties made by individual neural networks in prediction. It also employs specific discretization scheme, rule form, and fidelity evaluation mechanism. Experiments show that with different configurations, REFNE can extract rules with good fidelity that well explain the function of trained neural network ensembles, or rules with strong generalization ability that are even better than the trained neural network ensembles in prediction.

An ensemble is generated by training multiple component learners for a same task and then combining their predictions. In most ensemble algorithms, all the trained component learners are employed in constituting an ensemble. But recently, it has been shown that when the learners are neural networks, it may be better to ensemble some instead of all of the learners. In this paper, this claim is generalized to situations where the component learners are decision trees. Experiments show that ensembles generated by a selective ensemble algorithm, which selects some of the trained C4.5 decision trees to make up an ensemble, may be not only smaller in the size but also stronger in the generalization than ensembles generated by non-selective algorithms.

Classification requirements for real-world classification problems are often constrained by a given true positive or false positive rate to ensure that the classification error for the most important class is within a desired limit. For a sufficiently high true positive rate, this may result in the set-point being located somewhere in the flat portion of the ROC curve where the associated false positive rate is high. Any further classifier design will then attempt to reduce the false positive rate while maintaining the desired true positive rate. We call this type of performance requirements for classifier design the constrained performance requirement. This type of performance requirements is different from the accuracy maximization requirement and thus requires different strategies for classifier design. This paper is concerned with designing classifier ensembles under such constrained performance requirements. Classifier ensembles are one of the most significant advances in pattern recognition/classification in recent years and have been actively studied by many researchers. However, not much attention has been given to designing ensembles to satisfy constrained performance requirements. This paper attempts to identify and address some of design related issues associated with the constrained performance requirement. Specifically, we present a design strategy for designing neural network ensembles to satisfy constrained performance requirements, which is illustrated by designing a real-world classification problem. The results are compared to those from conventional design method. Keywords: classification; classifier ensembles; neural networks; constrained performance; diversity; accuracy; ROC; 1.

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 weightfixed, 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 di#erent 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.

Ensembling neural classifiers can significantly improve the generalization ability of classification systems. In this paper, GASEN, a genetic algorithm based selective ensemble method that has been shown to be excellent in ensembling neural regressors, is applied to neural classifiers. Experiments on four large data sets show that this method can generate ensembles of neural classifiers with stronger generalization ability than those generated by Bagging, Adaboost, or Arc-x4.