Adaptive Resonance Theory Model Research Articles

Bayesian ART for incomplete datasets

Adaptive Resonance Theory (ART) models allow for categorizing data in a fast and incremental manner. In particular, the Bayesian ART leverages Bayesian methodology to capture complex relationships between categories. While Bayesian methods are well-known for handling uncertainty, Bayesian ART models are at the mercy of a recurring foe: missing data. When data is missing, practitioners must rely on off-the-shelf solutions to impute the data before using Bayesian ART, effectively truncating the uncertainty quantification. To overcome such limitation, we (I) estimate the distribution of missing data entries using a Gaussian mixture model and (II) modify the three steps of Bayesian ART (category choice, matching, and update) to propagate the uncertainty around the missing entries. Experiments in a variety of tabular datasets show that, in general, our novel methodology leads to better results than using off-the-shelf imputation solutions. The performance gap becomes especially noticeable as the number of missing data entries increases.

An Ensemble Semi-Supervised Adaptive Resonance Theory Model With Explanation Capability for Pattern Classification

An Ensemble Semi-Supervised Adaptive Resonance Theory Model With Explanation Capability for Pattern Classification

Fuzzy adaptive resonance theory failure mode effect analysis non-healthcare setting for infectious disease: review

<span>Fuzzy adaptive resonance theory (ART) is an ART network that is developed as one of the alternative methods to evaluate risk priority number (RPN) in failure mode and effect analysis (FMEA). Not only is FMEA are common technique as an analysis tool in industrial sectors, but also, especially during the global emergency COVID-19 pandemic hits, FMEA is used in prevention and mitigation measures. Many alternative methods have been proposed. However, not many investigations use clustering models such as Fuzzy ART in FMEA. This paper aims to provide a comprehensive review and then propose a model for systematic risk analysis which implement the fuzzy ART model, named clustering- transmission causes and effects analysis (c-TCEA), for the prevention and mitigation of infectious diseases.</span>

An Enhanced Weight Update Method for Simplified ARTMAP to Classify Groundwater Data

The groundwater for aquatic purposes must be assessed prior to its consumption. Huge number of conventional methods are existing for assessing the quality of groundwater. The water quality index is one of the important conventional methods to assess the groundwater quality. But the conventional methods alone are not enough to assess groundwater quality as well as classify based on its purity. In this paper, we propose an enhanced weight update method for Simplified Fuzzy Adaptive Resonance Theory model to classify the groundwater quality depending on the relative weights of the groundwater quality parameters. Finding the optimal weights is the key to achieve better accuracy of the model, most of the nonlinear models fails to exhibit good accuracy if they fail to learn the optimal weights in the learning process. The aim of the work is to find the good fit between the predicted and the actual groundwater quality grades by identifying the optimal weights of the network by the enhanced weight update method. The Simplified Fuzzy Adaptive Resonance Theory map with the enhanced weight update method performance is justified by comparing it with the Simplified Fuzzy Adaptive Resonance Theory Map. The enhanced weight update method improves the accuracy of the Simplified Fuzzy Adaptive Resonance Theory Map in classifying and predicting the groundwater quality.

A Comparative Study on Fuzzy Clustering for Cloud Computing. Taking Web Service as a case

Abstract This study addresses the increasingly encountered challenge of data clustering. We present a comparative study to data clustering for cloud computing using Fuzzy C-MEANS and Adaptive Resonance Theory. To reduce variance and improve generalization ability, we used a resampling method based on 10-fold cross-validation. The typical initialization scheme is applied to improve the convergence speed of training and thus, reach the optimal solution. Experimental results on cloud computing datasets showed that the typical initialization-based Fuzzy Adaptive Resonance Theory model is effective and achieves improved accuracy for pattern recognition task compared to Fuzzy C-MEANS.

A survey of adaptive resonance theory neural network models for engineering applications

This survey samples from the ever-growing family of adaptive resonance theory (ART) neural network models used to perform the three primary machine learning modalities, namely, unsupervised, supervised and reinforcement learning. It comprises a representative list from classic to contemporary ART models, thereby painting a general picture of the architectures developed by researchers over the past 30 years. The learning dynamics of these ART models are briefly described, and their distinctive characteristics such as code representation, long-term memory, and corresponding geometric interpretation are discussed. Useful engineering properties of ART (speed, configurability, explainability, parallelization and hardware implementation) are examined along with current challenges. Finally, a compilation of online software libraries is provided. It is expected that this overview will be helpful to new and seasoned ART researchers.

Self-organizing neural networks for universal learning and multimodal memory encoding

Learning and memory are two intertwined cognitive functions of the human brain. This paper shows how a family of biologically-inspired self-organizing neural networks, known as fusion Adaptive Resonance Theory (fusion ART), may provide a viable approach to realizing the learning and memory functions. Fusion ART extends the single-channel Adaptive Resonance Theory (ART) model to learn multimodal pattern associative mappings. As a natural extension of ART, various forms of fusion ART have been developed for a myriad of learning paradigms, ranging from unsupervised learning to supervised learning, semi-supervised learning, multimodal learning, reinforcement learning, and sequence learning. In addition, fusion ART models may be used for representing various types of memories, notably episodic memory, semantic memory and procedural memory. In accordance with the notion of embodied intelligence, such neural models thus provide a computational account of how an autonomous agent may learn and adapt in a real-world environment. The efficacy of fusion ART in learning and memory shall be discussed through various examples and illustrative case studies.

Wireless network confidence level improvement via fusion adaptive resonance theory

One of the main hazards for the current internet community is the distributed denial of service attack (DDoS). Moreover, with the DDoS mechanisms being implicit in nature, the identification of it is very hard due to the unique characteristics of the normal traffic and useless packet sent to their victims by adversaries. The vulnerability of network mechanisms (VNM) accounts for maximal performance degradation on the system by the malicious users with the abundance resource availability. In addition, the Hash table based VNM suffers from longer waiting time with the attack size reflecting on the duplicate effect on the vulnerability. Rule-based firewall’s performance is evaluated by an analytical Queuing model that are exposed to standard traffic and DDoS attack flows where this model is based on embedded Markov chain (EMC). Queuing model based on EMC targets the different rule positions but mitigate DDoS attacks targeting bottom rules with minimal confidence in the network. To attain the confidence in the network, adaptive resonance theory (ART) is applied based on the semantic similarity measure. Furthermore, for learning inherent associations, a fusion method on the ART network is deployed. Fusion ART uses the multiple overlapping ART models. In this clusters are generated and associative mappings are coded transversely packet information in a real-time and continuous way. Semantic similarity category is combined in a fusion ART into predefined semantic categories to attain maximal confidence value in the network. ART scheme increases the trusted platform module by preventing the unnecessary DDoS attack. Fusion ART functionalities through ns2 simulation, produces the positive solution measured in terms of confidence rate in network, waiting time, CPU utilization, true positive rate, throughput.

Grandmother cohorts: multiple-scale brain compression dynamics during learning of object and sequence categories

ABSTRACTThis article summarises neural models of how invariant object categories are learned under conditions where eye movements freely scan a scene, and of how list categories, or chunks, are learned in response to sequences, or lists, of events that are temporarily stored in working memory. During both kinds of category learning, distributed information is compressed by a category learning process into compact groups of cells that can selectively respond to this information. Adaptive Resonance Theory models describe these learning processes and enable, in a limiting case, winner-take-all grandmother cells to be learned, even in a single trial, and rapidly activated during recall trials by bottom-up direct access. The degree of compression can vary with the amount of contextual evidence, and a distributed network of multiple categories may be needed to represent an object or event, all computed using localist mechanisms. Such a network is called a grandmother cohort in the current article.

DYNAMIC AND INCREMENTAL EXPLORATION STRATEGY IN FUSION ADAPTIVE RESONANCE THEORY FOR ONLINE REINFORCEMENT LEARNING

One of the fundamental challenges in reinforcement learning is to setup a proper balance between exploration and exploitation to obtain the maximum cummulative reward in the long run. Most protocols for exploration bound the overall values to a convergent level of performance. If new knowledge is inserted or the environment is suddenly changed, the issue becomes more intricate as the exploration must compromise the pre-existing knowledge. This paper presents a type of multi-channel adaptive resonance theory (ART) neural network model called fusion ART which serves as a fuzzy approximator for reinforcement learning with inherent features that can regulate the exploration strategy. This intrinsic regulation is driven by the condition of the knowledge learnt so far by the agent. The model offers a stable but incremental reinforcement learning that can involve prior rules as bootstrap knowledge for guiding the agent to select the right action. Experiments in obstacle avoidance and navigation tasks demonstrate that in the configuration of learning wherein the agent learns from scratch, the inherent exploration model in fusion ART model is comparable to the basic E-greedy policy. On the other hand, the model is demonstrated to deal with prior knowledge and strike a balance between exploration and exploitation.

Growing fuzzy topology adaptive resonance theory models with a push–pull learning algorithm

A new incrementally growing neural network model, called the growing fuzzy topology ART (GFTART) model, is proposed based on integrating the conventional fuzzy ART model with the incremental topology-preserving mechanism of the growing cell structure (GCS) model. This is in addition, to a new training algorithm, called the push–pull learning algorithm. The proposed GFTART model has two purposes: First, to reduce the proliferation of incrementally generated nodes in the F2 layer by the conventional fuzzy ART model based on replacing each F2 node with a GCS. Second, to enhance the class-dependent clustering representation ability of the GCS model by including the categorization property of the conventional fuzzy ART model. In addition, the proposed push–pull training algorithm enhances the cluster discriminating property and partially improves the forgetting problem of the training algorithm in the GCS model.

Consciousness CLEARS the mind

A full understanding of consciousness requires that we identify the brain processes from which conscious experiences emerge. What are these processes, and what is their utility in supporting successful adaptive behaviors? Adaptive Resonance Theory (ART) predicted a functional link between processes of Consciousness, Learning, Expectation, Attention, Resonance and Synchrony (CLEARS), including the prediction that "all conscious states are resonant states". This connection clarifies how brain dynamics enable a behaving individual to autonomously adapt in real time to a rapidly changing world. The present article reviews theoretical considerations that predicted these functional links, how they work, and some of the rapidly growing body of behavioral and brain data that have provided support for these predictions. The article also summarizes ART models that predict functional roles for identified cells in laminar thalamocortical circuits, including the six layered neocortical circuits and their interactions with specific primary and higher-order specific thalamic nuclei and nonspecific nuclei. These predictions include explanations of how slow perceptual learning can occur without conscious awareness, and why oscillation frequencies in the lower layers of neocortex are sometimes slower beta oscillations, rather than the higher-frequency gamma oscillations that occur more frequently in superficial cortical layers. ART traces these properties to the existence of intracortical feedback loops, and to reset mechanisms whereby thalamocortical mismatches use circuits such as the one from specific thalamic nuclei to nonspecific thalamic nuclei and then to layer 4 of neocortical areas via layers 1-to-5-to-6-to-4.

Dynamics of projective adaptive resonance theory model: the foundation of PART algorithm.

Projective adaptive resonance theory (PART) neural network developed by Cao and Wu recently has been shown to be very effective in clustering data sets in high dimensional spaces. The PART algorithm is based on the assumptions that the model equations of PART (a large scale and singularly perturbed system of differential equations coupled with a reset mechanism) have quite regular computational performance. This paper provides a rigorous proof of these regular dynamics of the PART model when the signal functions are special step functions, and provides additional simulation results to illustrate the computational performance of PART.

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks

A class of adaptive resonance theory (ART) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. Distributed ART neural networks combine the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multilayer perceptrons. With a winner-take-all code, the unsupervised model dART reduces to fuzzy ART and the supervised model dARTMAP reduces to fuzzy ARTMAP. With a distributed code, these networks automatically apportion learned changes according to the degree of activation of each coding node, which permits fast as well as slow learning without catastrophic forgetting. Distributed ART models replace the traditional neural network path weight with a dynamic weight equal to the rectified difference between coding node activation and an adaptive threshold. Thresholds increase monotonically during learning according to a principle of atrophy due to disuse. However, monotonic change at the synaptic level manifests itself as bidirectional change at the dynamic level, where the result of adaptation resembles long-term potentiation (LTP) for single-pulse or low frequency test inputs but can resemble long-term depression (LTD) for higher frequency test inputs. This paradoxical behavior is traced to dual computational properties of phasic and tonic coding signal components. A parallel distributed match–reset–search process also helps stabilize memory. Without the match–reset–search system, dART becomes a type of distributed competitive learning network.

Adaptive resonance associative map

This article introduces a neural architecture termed Adaptive Resonance Associative Map (ARAM) that extends unsupervised Adaptive Resonance Theory (ART) systems for rapid, yet stable, heteroassociative learning. ARAM can be visualized as two overlapping ART networks sharing a single category field. Although ARAM is simpler in architecture than another class of supervised ART models known as ARTMAP, it produces classification performance equivalent to that of ARTMAP. As ARAM network structure and operations are symmetrical, associative recall can be performed in both directions. With maximal vigilance settings, ARAM encodes pattern pairs explicitly as cognitive chunks and thus guarantees perfect storage and recall of an arbitrary number of arbitrary pattern pairs. Simulations on an iris plant and a sonar return recognition problems compare ARAM classification performance with that of counterpropagation network, K-nearest neighbor system, and back propagation network. Associative recall experiments on two pattern sets show that, besides the advantages of fast learning, guaranteed perfect storage, and full memory capacity, ARAM produces a stronger noise immunity than Bidirectional Associative Memory (BAM).

A new art-based neural architecture for pattern classification and image enhancement without prior knowledge

The visual field is not perceived as an array of independent picture points. Instead, it is usually seen as consisting of a relatively small number of patterns. Whenever a picture is converted from one form to another, e.g. imaged, copied, scanned, transmitted, or displayed, the “quality” of the output picture may be lower than that of the input. In the absence of knowledge about how the given picture was actually degraded, it is difficult to predict in advance how effective a particular enhancement method will be. In this paper, the formulation of a new neural architecture is presented based on adaptive resonance theory (ART), for the pattern classification and image enhancement in the presence of noise without prior knowledge. The underlying theory and the improvement of the ART model are first investigated in classifying optical character patterns. Based upon the result, the two-layer ART model is incorporated into a four-layer neural network which is proposed whereby pre-established generalized enhancement templates are used as region or contour detection exemplars in order to fill in the gaps and eliminate the noise in a pattern without any prior knowledge of the image itself.

Neural network formalization of the hungarian party-state system

A description of the decision-making structure of the Hungarian Party-state system, based on empirical studies, is offered. The structure is divided into three parts: the formal hierarchies, the interlinking threads, and the feedback connections. The working mechanism, the sources of cohesion, and the maintenance of the system are explained. The working mechanism of the structure reveals pattern-recognition-type decision making and close similarity to the adaptive resonance theory (ART) of competitive learning. The observed analogy is followed throughout the structure. Based on the ART model, we offer a mathematical description of the properties of the structure that could, in principle, be quantified if the model parameters were to be determined by further empirical studies. Properties of the structure are qualitatively analyzed with the help of this mathematical model. The self-similar or fractal property of the structure makes it possible to analyze some features of other Party-state systems.

Cerebral and Cerebellar Models of Language Learning

Recent research in ‘connectionism’ has awakened interest in parallel models of language. The most widely-reported architectures model cerebellar cortex. Language, however, is principally learned by cerebral cortex. In cerebral anatomies, Peircean ‘surprising events’ cause ‘rebounds’: revolutions in which dominant synergies of dipole fields (rules) are overthrown and replaced by new synergies. Grossberg's Adaptive Resonance Theory (ART) describes such anatomies. The ART model is presented as a general framework for explaining common linguistic phenomena such as fossilization, categorical perception, vowel phonemicization, and linguistic rule formation. The performance of cerebral ART models is compared with that of cerebellar models (Parallel Distributed Processing, Boltzmann machines). In conclusion, ART is proposed as a basis for unifying language learning theories with each other and with praxis.