A hybrid ART-GRNN online learning neural network with a ε-insensitive loss function

In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.

Knowledge mobilization on decision making for school improvement : Canadian principals learning network.

Principals duties have expanded beyond instructional leadership. Roles now include being curriculum leader, supervisor, manager, head of finance, administration, compliance, and legal matters, and so on. These additional responsibilities impact their decision-making in relation to teaching, learning and school improvement in general. How, and on what basis, they make these decisions is crucial both to their development as instructional leaders and to educational reform processes. To contribute to knowledge on principals’ decision making skills, we have created a strategic knowledge mobilization initiative called 'Canadian Principals Learning Network (CPLN)'. Through a variety of face-to-face and online activities, it collaboratively links together an international group of practicing principals and university-based researchers with related expertise. This paper describes the initiative and outcomes.

Evaluation of the fuzzy ARTMAP neural network using off-line and on-line learning strategies

This paper describes an experimental study of the Fuzzy ARTMAP (FAM) neural network as an autonomous learning system for pattern classification tasks. A benchmark database of radar signals from ionosphere has been employed for the system to classify arbitrary sequences of pattern into distinct categories. A number of simulations have been conducted systematically to evaluate the applicability and usefulness of FAM in this context. First, we identify the 'optimum' parameter settings of FAM for the problem at hand, and investigate the effects of different training schemes and learning rules on classification results, using an off-line learning methodology. We then examine a voting strategy to improve classification accuracy by combining results from multiple FAM classifiers. In addition to off-line learning, we evaluate the prospect of using FAM as an autonomously learning pattern classification system for on-line, non-stationary environments. The performance of FAM is comparable with other reported results, but with the added advantage of on-line and incremental learning.

Rule learning and extraction using a hybrid neural network : a case study on fault detection and diagnosis

A hybrid network, based on the integration of Fuzzy ARTMAP (FAM) and the Rectangular Basis Function Network (RecBFN), is proposed for rule learning and extraction problems. The underlying idea for such integration is that FAM operates as a classifier to cluster data samples based on similarity, while the RecBFN acts as a “compressor” to extract and refine knowledge learned by the trained FAM network. The hybrid network is capable of classifying data samples incrementally as well as of acquiring rules directly from data samples for explaining its predictions. To evaluate the effectiveness of the hybrid network, it is applied to a fault detection and diagnosis task by using a set of real sensor data collected from a Circulating Water (CW) system in a power generation plant. The rules extracted from the network are analyzed and discussed, and are found to be in agreement with experts’ opinions used in maintaining the CW system.

Transfer learning using the online Fuzzy Min-Max neural network

In this paper, we present an empirical analysis on transfer learning using the Fuzzy Min–Max (FMM) neural network with an online learning strategy. Three transfer learning benchmark data sets, i.e., 20 Newsgroups, WiFi Time, and Botswana, are used for evaluation. In addition, the data samples are corrupted with white Gaussian noise up to 50 %, in order to assess the robustness of the online FMM network in handling noisy transfer learning tasks. The results are analyzed and compared with those from other methods. The outcomes indicate that the online FMM network is effective for undertaking transfer learning tasks in noisy environments.

Three algorithms for learning artificial neural network: A comparison for induction motor flux estimation

This paper presents a comparative study of three algorithms for learning artificial neural network. As neural estimator, back-propagation (BP) algorithm, uncorrelated real time recurrent learning (URTRL) algorithm and correlated real time recurrent learning (CRTRL) algorithm are used in the present work to learn the artificial neural network (ANN). The approach proposed here is based on the flux estimation of high performance induction motor drives. Simulation of the drive system was carried out to study the performance of the motor drive. It is observed that the proposed CRTRL algorithm based methodology provides better performance than the BP and URTRL algorithm based technique. The proposed method can be used for accurate measurement of the rotor flux.