Image Analysis and Computer Vision

With the rapid development of the web, the needfor text classification of large data volumes is permanentlygrowing. Texts represented as bags-of-words possess usually veryhigh dimensionality in the input space and often also in theoutput space if labeled with many categories. As a result, neuralclassifiers should be adapted to such large-scale data. We presenthere a well scalable extension to the fuzzy Adaptive ResonanceAssociative Map (ARAM) neural network which was speciallydeveloped for high-dimensional and large data. This extensionaims at increasing the classification speed by adding an extraART layer for clustering learned prototypes into large clusters. In this case the activation of all prototypes can be replacedby the activation of a small fraction of them, leading to asignificant reduction of the classification time. This extension canbe especially useful for multi-label classification tasks.

HARAM: A Hierarchical ARAM Neural Network for Large-Scale Text Classification

Multilevel categorization is investigated within the context of analog activity patterns on the output layer of an ART 2 network. The ART 2 network parameters are analyzed in terms of stable category formation and in terms of the number of nodes in the output layer that can become most active. The resulting activity patterns on the output layer demonstrate a multilevel category structure based on the relative differences between patterns that exist for many different values of the vigilance parameter. We have shown that the information contained in the output analog patterns can be interpreted in several different ways, which is not possible when the category is represented by a single winning node. Also, favorable comparisons are also demonstrated between the category structure emerging from the set of category patterns and principles of categorization in psychology and neurobiology.

Multilevel category structure in the ART-2 network

Availability of large full-text document collections in electronic form has created a need for tools and techniques that assist users in organizing these collections. Document clustering is one of the popular methods used for this purpose. In this paper, we propose the neural network based document clustering method by using a hierarchically organized network built up from independent Self-Organizing Map (SOM) and Adaptive Resonance Theory (ART) neural networks. We present clustering results using the REUTERS corpus and show an improvement in clustering performance using both entropy and F-measure as evaluation measures.

Document clustering using hierarchical SOMART neural network

This paper presents a novel adaptive resonance theory (ART)-based modular architecture for unsupervised learning, namely the distributed dual vigilance fuzzy ART (DDVFA). DDVFA consists of a global ART system whose nodes are local fuzzy ART modules. It is equipped with the distinctive features of distributed higher-order activation and match functions, using dual vigilance parameters responsible for cluster similarity and data quantization. Together, these allow DDVFA to perform unsupervised modularization, create multi-prototype clustering representations, retrieve arbitrarily-shaped clusters, and control its compactness. Another important contribution is the reduction of order-dependence, an issue that affects any agglomerative clustering method. This paper demonstrates two approaches for mitigating order-dependence: preprocessing using visual assessment of cluster tendency (VAT) or postprocessing using a novel Merge ART module. The former is suitable for batch processing, whereas the latter can be used in online learning. Experimental results in the online learning mode carried out on 30 benchmark data sets show that DDVFA cascaded with Merge ART statistically outperformed the best other ART-based systems when samples were randomly presented. Conversely, they were found to be statistically equivalent in the offline mode when samples were pre-processed using VAT. Remarkably, performance comparisons to non-ART-based clustering algorithms show that DDVFA (which learns incrementally) was also statistically equivalent to the non-incremental (offline) methods of DBSCAN, single linkage hierarchical agglomerative clustering (HAC), and k-means, while retaining the appealing properties of ART. Links to the source code and data are provided. Considering the algorithm's simplicity, online learning capability, and performance, it is an ideal choice for many agglomerative clustering applications.

Distributed dual vigilance fuzzy adaptive resonance theory learns online, retrieves arbitrarily-shaped clusters, and mitigates order dependence

In this paper, we propose a cascade fuzzy ART (CFART) neural network which can be used as an extensible database in a model-based object recognition system. The proposed CFART networks can accept both binary and continuous inputs. Besides, it preserves the prominent characteristics of a fuzzy ART network and extends the fuzzy ART's capability toward a hierarchical class representation of input patterns. The learning processes of the proposed network are unsupervised and self-organizing, which include coupled top-down searching and bottom-up learning processes. In addition, a global searching tree is built to speed up the learning and recognition processes.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Cascade fuzzy ART: a new extensible database for model-based object recognition

This article addresses the problem of segmenting objects into parts using stereo images. There are three components in the part segmentation process: surface segmentation, region grouping, and volumetric models (superquadrics) recovery/segmentation. The surface segmentation process segments the image into a set of regions such that each region represents a smooth surface. The region grouping process merges the segmented regions into parts. Finally the process of volumetric models recovery/segmentation recovers the part model and segments that part into smaller parts if necessary. Because we use both surface and volumetric models to drive the part segmentation process, we can capture more geometric properties of the object, and the application domain of our approach is broader than that of previous approaches. The performance of the proposed system is demonstrated with real images and synthetic images. Experimental results show that the system is stable and capable of handling a variety of objects.©1994 John Wiley & Sons Inc

Part segmentation from stereo

In this paper, a cascade fuzzy ART (CFART) network is developed and applied to 3D object recognition. The proposed CFART network contains multiple layers which can express a hierarchical representation of an input pattern. The learning processes of the proposed network are unsupervised and self-organizing, which include a top-down search process and a bottom-up learning process. The proposed CFART can accept both binary and analog inputs. With fast learning and categorization capabilities, the proposed network is capable of acting as an extensible database, providing a multi-resolutional representation of 3D objects. In the experiments, we use superquadrics as a demonstration example.

Wei-Chung Lin

Papers

Cascade fuzzy ART: a new extensible database for model-based object recognition

Part segmentation from stereo

CFART: a multi-resolutional adaptive resonance system