Adaptive Resonance Theory Network Research Articles

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>

CORRIGENDUM to Pre-trained Back Propagation based Adaptive Resonance Theory Network for Adaptive Learning

CORRIGENDUM to Pre-trained Back Propagation based Adaptive Resonance Theory Network for Adaptive Learning

Self-Organizing Memory Based on Adaptive Resonance Theory for Vision and Language Navigation

Vision and Language Navigation (VLN) is a task in which an agent needs to understand natural language instructions to reach the target location in a real-scene environment. To improve the model ability of long-horizon planning, emerging research focuses on extending the models with different types of memory structures, mainly including topological maps or a hidden state vector. However, the fixed-length hidden state vector is often insufficient to capture long-term temporal context. In comparison, topological maps have been shown to be beneficial for many robotic navigation tasks. Therefore, we focus on building a feasible and effective topological map representation and using it to improve the navigation performance and the generalization across seen and unseen environments. This paper presents a S elf-organizing Memory based on Adaptive Resonance Theory (SMART) module for incremental topological mapping and a framework for utilizing the SMART module to guide navigation. Based on fusion adaptive resonance theory networks, the SMART module can extract salient scenes from historical observations and build a topological map of the environmental layout. It provides a compact spatial representation and supports the discovery of novel shortcuts through inferences while being explainable in terms of cognitive science. Furthermore, given a language instruction and on top of the topological map, we propose a vision–language alignment framework for navigational decision-making. Notably, the framework utilizes three off-the-shelf pre-trained models to perform landmark extraction, node–landmark matching, and low-level controlling, without any fine-tuning on human-annotated datasets. We validate our approach using the Habitat simulator on VLN-CE tasks, which provides a photo-realistic environment for the embodied agent in continuous action space. The experimental results demonstrate that our approach achieves comparable performance to the supervised baseline.

Pretrained back propagation based adaptive resonance theory network for adaptive learning

The deep convolutional neural network performs well in current computer vision tasks. However, most of these models are trained on an aforehand complete dataset. New application scenario data sets should be added to the original training data set for model retraining when application scenarios change significantly. When the scenario changes only slightly, the transfer learning can be used for network training by a small data set of new scenarios to adapt it to the new scenario. In actual application, we hope that our model has bio-like intelligence and can adaptively learn new knowledge. This paper proposes a pretrained adaptive resonance network (PAN) based on the CNN and an intra-node back propagation ART network, which can adaptively learn new knowledge using prior information. The PAN network explores the difference between the new data and the stored information and learns this difference to realize the adaptive growth of the network. The model is testified on the MNIST and Omniglot data set, which show the effectiveness of PAN in adaptive incremental learning and its competitive classification accuracy.

Vision-Based Topological Mapping and Navigation With Self-Organizing Neural Networks.

Spatial mapping and navigation are critical cognitive functions of autonomous agents, enabling one to learn an internal representation of an environment and move through space with real-time sensory inputs, such as visual observations. Existing models for vision-based mapping and navigation, however, suffer from memory requirements that increase linearly with exploration duration and indirect path following behaviors. This article presents e -TM, a self-organizing neural network-based framework for incremental topological mapping and navigation. e -TM models the exploration trajectories explicitly as episodic memory, wherein salient landmarks are sequentially extracted as "events" from streaming observations. A memory consolidation procedure then performs a playback mechanism and transfers the embedded knowledge of the environmental layout into spatial memory, encoding topological relations between landmarks. Fusion adaptive resonance theory (ART) networks, as the building block of the two memory modules, can generalize multiple input patterns into memory templates and, therefore, provide a compact spatial representation and support the discovery of novel shortcuts through inferences. For navigation, e -TM applies a transfer learning paradigm to integrate human demonstrations into a pretrained locomotion network for smoother movements. Experimental results based on VizDoom, a simulated 3-D environment, have shown that, compared to semiparametric topological memory (SPTM), a state-of-the-art model, e -TM reduces the time costs of navigation significantly while learning much sparser topological graphs.

SR-EM: Episodic Memory Aware of Semantic Relations Based on Hierarchical Clustering Resonance Network.

An intelligent robot requires episodic memory that can retrieve a sequence of events for a service task learned from past experiences to provide a proper service to a user. Various episodic memories, which can learn new tasks incrementally without forgetting the tasks learned previously, have been designed based on adaptive resonance theory (ART) networks. The conventional ART-based episodic memories, however, do not have the adaptability to the changing environments. They cannot utilize the retrieved task episode adaptively in the working environment. Moreover, if a user wants to receive multiple services of the same kind in a given situation, the user should repeatedly command multiple times. To tackle these limitations, in this article, a novel hierarchical clustering resonance network (HCRN) is proposed, which has a high clustering performance on multimodal data and can compute the semantic relations between learned clusters. Using HCRN, a semantic relation-aware episodic memory (SR-EM) is designed, which can adapt the retrieved task episode to the current working environment to carry out the task intelligently. Experimental simulations demonstrate that HCRN outperforms the conventional ART in terms of clustering performance on multimodal data. Besides, the effectiveness of the proposed SR-EM is verified through robot simulations for two scenarios.

Method of Robot Episode Cognition Based on Hippocampus Mechanism

This paper proposes a method to realize the robot’s self-learning of environment by using an episode cognition model inspired by the hippocampus. The episode cognition map is suitable for robot navigation in an unknown environment, which solves the problem of robustness of the robot’s perception in complex and dynamic environments. The model called the hippocampus episode cognitive network (HEC), is based on the hippocampus CA1, CA3, and the dentate gyrus, and combined with the adaptive resonance theory (ART) network. It extract new events through the incremental generation of cognitive neurons, and encode the events into episodes through space-time connections. The episode nodes can be connected to generate an episode cognition map. This method can learn, store, and update information for autonomous mobile robots in an unknown environment. Based on the episode cognitive map, the path trajectory can be predicted through the playback of the episode neuron. The experimental results on the mobile robot show that this method can effectively improve the robot’s adaptability for location and mapping in a complex and dynamic environment.

Tour Planning Design for Mobile Robots Using Pruned Adaptive Resonance Theory Networks

The development of intelligent algorithms for controlling autonom- ous mobile robots in real-time activities has increased dramatically in recent years. However, conventional intelligent algorithms currently fail to accurately predict unexpected obstacles involved in tour paths and thereby suffer from inefficient tour trajectories. The present study addresses these issues by proposing a potential field integrated pruned adaptive resonance theory (PPART) neural network for effectively managing the touring process of autonomous mobile robots in real-time. The proposed system is implemented using the AlphaBot platform, and the performance of the system is evaluated according to the obstacle prediction accuracy, path detection accuracy, time-lapse, tour length, and the overall accuracy of the system. The proposed system provide a very high obstacle prediction accuracy of 99.61%. Accordingly, the proposed tour planning design effectively predicts unexpected obstacles in the environment and thereby increases the overall efficiency of tour navigation.

Adaptive Developmental Resonance Network.

Adaptive resonance theory (ART) networks, including developmental resonance network (DRN), basically use a vigilance parameter as a hyperparameter to determine whether a current input can belong to any existing categories or not. The problem here is that the clustering quality of those networks is sensitive to the vigilance parameter so that the users are required to fine-tune the parameter delicately beforehand. Another problem is that those networks only deal with a hyperrectangular decision boundary, which means they cannot learn categories of arbitrary shape. In addition, the order of data processing is a critical factor to categorize clusters correctly because each category can expand its boundary into the areas of other categories erroneously. To deal with these problems, we propose an advanced version of DRN, Adaptive DRN (A-DRN), which learns the vigilance parameters assigned for individual category nodes as well as category weights. The proposed A-DRN combines close categories to construct a cluster that contains the categories identifying a cluster boundary of arbitrary shape. Our A-DRN also employs a sliding window. The sliding window buffers sequential data points to presume the data distribution roughly, which helps our network to have a robust and consistent performance to a random order of input data. Through the experiments, we empirically demonstrate the effectiveness of A-DRN in both synthetic and real-world benchmark data sets.

A Brain-Inspired Adaptive Space Representation Model Based on Grid Cells and Place Cells.

Grid cells and place cells are important neurons in the animal brain. The information transmission between them provides the basis for the spatial representation and navigation of animals and also provides reference for the research on the autonomous navigation mechanism of intelligent agents. Grid cells are important information source of place cells. The supervised learning and unsupervised learning models can be used to simulate the generation of place cells from grid cell inputs. However, the existing models preset the firing characteristics of grid cell. In this paper, we propose a united generation model of grid cells and place cells. First, the visual place cells with nonuniform distribution generate the visual grid cells with regional firing field through feedforward network. Second, the visual grid cells and the self-motion information generate the united grid cells whose firing fields extend to the whole space through genetic algorithm. Finally, the visual place cells and the united grid cells generate the united place cells with uniform distribution through supervised fuzzy adaptive resonance theory (ART) network. Simulation results show that this model has stronger environmental adaptability and can provide reference for the research on spatial representation model and brain-inspired navigation mechanism of intelligent agents under the condition of nonuniform environmental information.

Individualized AI Tutor Based on Developmental Learning Networks

In recent years, in the field of education technology, artificial intelligence tutors have come to be expected to provide individualized educational services to help learners achieve high levels of academic success. To this end, AI tutors need to be able to understand the current status and preferences of a learner and then suggest appropriate learning contents accordingly. However, it is challenging to monitor learner status and preferences continually and to recommend appropriate educational services. In this paper, we propose an individualized AI tutor as an integrated system of three developmental learning networks (DLNs) by extending a deep adaptive resonance theory (Deep ART) network, a neural network capable of incremental learning. Specifically, the learner status DLN is able to easily add new input channels about learner status without disrupting existing classifiers. The learner preference DLN is to categorize learner preferences based on frequency as well as sequence of events. The learner experience DLN is updated to immediately reflect alteration of the educational effectiveness in the current classification. Our AI tutor is currently embedded in a commercialized mobile application for teaching the Korean language to children. Experimental results show that the AI tutor application efficiently helps children learn the Korean language.

Infrared dim target detection method based on the fuzzy accurate updating symmetric adaptive resonance theory

Motivated by the human visual system, we propose an infrared dim target detection method that is based on a fuzzy accurate updating symmetric adaptive resonance theory network. From the bottom-up perspective, the regions of interest (ROIs) are extracted using a difference of Gaussians at multiple scales and our designed ROI model in a saliency map. From the top-down perspective, five feature categories are extracted using the ROI model, which are used to train the proposed Fuzzy AUSART network. The well-trained network realizes the true identification of all ROI candidates. The results of the receiver operating characteristic (ROC) curves verify that the proposed method can better adapt to different circumstances and targets in our experiment. The average detection accuracy of the Fuzzy AUSART is improved by 15.4%, and the average F1 index of the proposed method is higher than six typical comparison methods by more than a factor of 2.48.

ConvART: Improving Adaptive Resonance Theory for Unsupervised Image Clustering

While supervised learning techniques have become increasinglyadept at separating images into different classes, these techniquesrequire large amounts of labelled data which may not always beavailable. We propose a novel neuro-dynamic method for unsuper-vised image clustering by combining 2 biologically-motivated mod-els: Adaptive Resonance Theory (ART) and Convolutional Neu-ral Networks (CNN). ART networks are unsupervised clustering al-gorithms that have high stability in preserving learned informationwhile quickly learning new information. Meanwhile, a major prop-erty of CNNs is their translation and distortion invariance, whichhas led to their success in the domain of vision problems. Byembedding convolutional layers into an ART network, the usefulproperties of both networks can be leveraged to identify differentclusters within unlabelled image datasets and classify images intothese clusters. In exploratory experiments, we demonstrate thatthis method greatly increases the performance of unsupervisedART networks on a benchmark image dataset.

Dual vigilance fuzzy adaptive resonance theory

Clusters retrieved by generic Adaptive Resonance Theory (ART) networks are limited to their internal categorical representation. This study extends the capabilities of ART by incorporating multiple vigilance thresholds in a single network: stricter (data compression) and looser (cluster similarity) vigilance values are used to obtain a many-to-one mapping of categories-to-clusters. It demonstrates this idea in the context of Fuzzy ART, presented as Dual Vigilance Fuzzy ART (DVFA), to improve the ability to capture clusters with arbitrary geometry. DVFA outperformed Fuzzy ART for the datasets in our experiments while yielding a statistically-comparable performance to another more complex, multi-prototype Fuzzy ART-based architecture.

Developmental Resonance Network.

Adaptive resonance theory (ART) networks deal with normalized input data only, which means that they need the normalization process for the raw input data, under the assumption that the upper and lower bounds of the input data are known in advance. Without such an assumption, ART networks cannot be utilized. To solve this problem and improve the learning performance, inspired by the ART networks, we propose a developmental resonance network (DRN) by employing new techniques of a global weight and node connection and grouping processes. The proposed DRN learns the global weight converging to the unknown range of the input data and properly clusters by grouping similar nodes into one. These techniques enable DRN to learn the raw input data without the normalization process while retaining the stability, plasticity, and memory usage efficiency without node proliferation. Simulation results verify that our DRN, applied to the unsupervised clustering problem, can cluster raw data properly without a prior normalization process.

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.

Hierarchical emotional episodic memory for social human robot collaboration

For social human robot collaboration, robots need to effectively remember human experiences and manage emotional experiences as well as repetitive experiences. To implement these functions, the hierarchical emotional episodic memory, using deep adaptive resonance theory network, is proposed in this paper. The proposed memory not only learns emotional experiences, but also has the ability to anticipate future emotional situations. Two parameter modulation processes, delayed consolidation and instant update, are provided. These make emotional experiences reinforce faster, remain for longer, and become more stable and sensitive to analogous experiences. Simulation analysis is conducted to verify the proposed memory, and an experiment is carried out in a kitchen environment to demonstrate social human robot collaboration.

Semantic Memory Modeling and Memory Interaction in Learning Agents

Semantic memory plays a critical role in reasoning and decision making. It enables an agent to abstract useful knowledge learned from its past experience. Based on an extension of fusion adaptive resonance theory network, this paper presents a novel self-organizing memory model to represent and learn various types of semantic knowledge in a unified manner. The proposed model, called fusion adaptive resonance theory for multimemory learning, incorporates a set of neural processes, through which it may transfer knowledge and cooperate with other long-term memory systems, including episodic memory and procedural memory. Specifically, we present a generic learning process, under which various types of semantic knowledge can be consolidated and transferred from the specific experience encoded in episodic memory. We also identify and formalize two forms of memory interactions between semantic memory and procedural memory, through which more effective decision making can be achieved. We present experimental studies, wherein the proposed model is used to encode various types of semantic knowledge in different domains, including a first-person shooting game called Unreal Tournament, the Toads and Frogs puzzle, and a strategic game known as StarCraft Broodwar. Our experiments show that the proposed knowledge transfer process from episodic memory to semantic memory is able to extract useful knowledge to enhance the performance of decision making. In addition, cooperative interaction between semantic knowledge and procedural skills can lead to a significant improvement in both learning efficiency and performance of the learning agents.

Incremental clustering of sonar images using self-organizing maps combined with fuzzy adaptive resonance theory

In this paper we introduce a new unsupervised segmentation algorithm for textured sonar images. A Dynamic Self-Organizing Maps (DSOM) algorithm capable of incremental learning has been developed to automatically cluster the input data into relevant classes of seabed. DSOM algorithm is an extension of classical Self-Organizing Maps (SOM) algorithm combined with Adaptive Resonance Theory (ART) technique. The proposed approach is based on growing map size during learning processes. Starting with a minimal number of neurons, the map size increases dynamically and the growth is controlled by the vigilance threshold of the ART network. To assess the consistency of the proposed approach, the DSOM algorithm is first tested on simulated data sets and then applied on real sidescan sonar images. The results obtained using the proposed approach demonstrate its capability to successfully cluster sonar images into their relevant seabed classes, very close to those resulting from human expert interpretation.

Models of self-organizing artificial neural networks to identify stationary industrial sources of air pollution

A problem of identifying one particular or a few possible pollution sources that are responsible for the deterioration of the air quality as a result of exceeding the standards of the maximum permissible emissions is considered. A model problem for a group of spatially divided stationary permanent industrial sources is solved. A statement identifying the problem and a method to solve it using two architectures of artificial neural networks, Kohonen’s networks for learning vector quantization with fixed and adaptive structures, as well as adaptive resonance theory network for analog inputs (ART-2), are presented. The method consists of clustering the data provided by self-learning algorithms (unsupervised learning). Estimation equations are given and operation algorithms of Kohonen’s and adaptive resonance theory networks at different life cycle stages are described. The results of the solution of the model problem that are obtained using each network is performed are comparatively analyzed.