OnARTMAP: A Fuzzy ARTMAP-based Architecture

Fuzzy ARTMAP (FAM) copes with the stability-plasticity dilemma by the adaptive resonance theory (ART). Despite such an advantage, Fuzzy ARTMAP suffers from a category proliferation problem, which leads to a high number of categories and a decrease in performance for unseen patterns. Such drawbacks are mainly caused by the overlapping region (noise) between classes. To overcome these drawbacks, we propose a Fuzzy ARTMAP-based architecture robust to noise, named OnARTMAP, for both online and batch learning. Our neural networks (OnARTMAP₁ and OnARTMAP₂) proposed for batch learning have a two-stage learning process, while our neural network (OnARTMAP_o) for online and incremental learning has just a single iterative process. Two new modules are proposed, the overlapping region detection module (ORDM) and another one similar to ART_a, called ART_c. The ORDM finds the overlapping region between categories, while the ART_c computes and stores special categories for overlapping areas. In our architecture proposal, the weights for ordinary categories are estimated from data outside the overlapping area. An alternative to the second stage strategy for batch learning is presented and focuses on improving the generalization performance. On the basis of our achievements, one can infer that OnARTMAP can improve the generalization performance and decrease the number of categories. Our proposals were applied to artificial and real datasets, as well as were compared with several counterparts (Fuzzy ARTMAP, ART-EMAP, μARTMAP, and BARTMAP).

Adaptive Scaling of Cluster Boundaries for Large-Scale Social Media Data Clustering

The large scale and complex nature of social media data raises the need to scale clustering techniques to big data and make them capable of automatically identifying data clusters with few empirical settings. In this paper, we present our investigation and three algorithms based on the fuzzy adaptive resonance theory (Fuzzy ART) that have linear computational complexity, use a single parameter, i.e., the vigilance parameter to identify data clusters, and are robust to modest parameter settings. The contribution of this paper lies in two aspects. First, we theoretically demonstrate how complement coding, commonly known as a normalization method, changes the clustering mechanism of Fuzzy ART, and discover the vigilance region (VR) that essentially determines how a cluster in the Fuzzy ART system recognizes similar patterns in the feature space. The VR gives an intrinsic interpretation of the clustering mechanism and limitations of Fuzzy ART. Second, we introduce the idea of allowing different clusters in the Fuzzy ART system to have different vigilance levels in order to meet the diverse nature of the pattern distribution of social media data. To this end, we propose three vigilance adaptation methods, namely, the activation maximization (AM) rule, the confliction minimization (CM) rule, and the hybrid integration (HI) rule. With an initial vigilance value, the resulting clustering algorithms, namely, the AM-ART, CM-ART, and HI-ART, can automatically adapt the vigilance values of all clusters during the learning epochs in order to produce better cluster boundaries. Experiments on four social media data sets show that AM-ART, CM-ART, and HI-ART are more robust than Fuzzy ART to the initial vigilance value, and they usually achieve better or comparable performance and much faster speed than the state-of-the-art clustering algorithms that also do not require a predefined number of clusters.

Stochastic competitive learning in complex networks

Competitive learning is an important machine learning approach which is widely employed in artificial neural networks. In this paper, we present a rigorous definition of a new type of competitive learning scheme realized on large-scale networks. The model consists of several particles walking within the network and competing with each other to occupy as many nodes as possible, while attempting to reject intruder particles. The particle's walking rule is composed of a stochastic combination of random and preferential movements. The model has been applied to solve community detection and data clustering problems. Computer simulations reveal that the proposed technique presents high precision of community and cluster detections, as well as low computational complexity. Moreover, we have developed an efficient method for estimating the most likely number of clusters by using an evaluator index that monitors the information generated by the competition process itself. We hope this paper will provide an alternative way to the study of competitive learning..

Comparison between analog and digital neural network implementations for range-finding applications

A neural network (NN) was developed in order to increase the distance range of a phase-shift laser range finder and to achieve surface recognition, by using two photoelectrical signals issued from the measurement system. The NN architecture consists of a multilayer perceptron (MLP) with two inputs, three neurons in the hidden layer, and one output. Depending on the application, the NN output has to resolve the ambiguity due to phase-shift measurement by linearizing the inverse of the square law, or to indicate an output voltage corresponding to the tested surface. This embedded system dedicated to optoelectronic measurements was successfully tested with an analog NN, implemented in 0.35- microm complimentary metal-oxide-semiconductor (CMOS) technology, resulting in a threefold increase in the distance range with respect to the one limited by the phase-shift measurement, and by discriminating four types of surfaces (a plastic surface, glossy paper, a painted wall, and a porous surface), at a remote distance between the range finder and the target varying from 0.5 m up to 1.25 m and with a laser beam angle varying between -pi/6 and pi/6 with respect to the target. In this type of application, NN analog implementation provides many advantages, notably use of a small silicon area, low power consumption and no analog-to-digital conversions (ADCs). Nevertheless, digital implementation allows ease of conception and reconfigurability and an embedded weight and bias update. This paper presents the complete measurement system and a comparison between both types of implementation, by developing the advantages and drawbacks relative to each method. An optimized mixed architecture, using both techniques, is then proposed and discussed at the end of the paper.