Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Databases and Information Systems (116)
- Software Engineering (80)
- Artificial Intelligence and Robotics (37)
- Engineering (37)
- Computer Engineering (35)
-
- Graphics and Human Computer Interfaces (32)
- Information Security (24)
- Digital Communications and Networking (15)
- Social and Behavioral Sciences (15)
- Theory and Algorithms (15)
- Public Affairs, Public Policy and Public Administration (11)
- Programming Languages and Compilers (10)
- Transportation (10)
- Business (8)
- Computer and Systems Architecture (8)
- Numerical Analysis and Scientific Computing (6)
- Systems Architecture (6)
- Data Storage Systems (4)
- Communication (3)
- Management Information Systems (3)
- Social Media (3)
- Technology and Innovation (3)
- Medicine and Health Sciences (2)
- Operations Research, Systems Engineering and Industrial Engineering (2)
- Public Health (2)
- Applied Mathematics (1)
- Arts and Humanities (1)
- Keyword
-
- Neural networks (12)
- Graph neural networks (11)
- Deep learning (9)
- Reinforcement learning (9)
- Task analysis (8)
-
- Training (8)
- Graph Neural Networks (7)
- Neural network (6)
- Security (6)
- Deep learning testing (5)
- Deep neural networks (5)
- Network embedding (5)
- Adaptive Resonance Theory (4)
- Categorization (4)
- Cloud computing (4)
- Clustering (4)
- Computer architecture (4)
- Finance (4)
- Meta-learning (4)
- Multimodality (4)
- Networks (4)
- Neural Networks (4)
- Neurons (4)
- Supervised learning (4)
- Uncertainty (4)
- Adaptive resonance theory (3)
- Adaptive systems (3)
- Adversarial attack (3)
- Anomaly Detection (3)
- Attention mechanisms (3)
- Publication Year
- Publication
- Publication Type
Articles 331 - 345 of 345
Full-Text Articles in OS and Networks
Modified Art 2a Growing Network Capable Of Generating A Fixed Number Of Nodes, Ji He, Ah-Hwee Tan, Chew-Lim Tan
Modified Art 2a Growing Network Capable Of Generating A Fixed Number Of Nodes, Ji He, Ah-Hwee Tan, Chew-Lim Tan
Research Collection School Of Computing and Information Systems
This paper introduces the Adaptive Resonance Theory under Constraint (ART-C 2A) learning paradigm based on ART 2A, which is capable of generating a user-defined number of recognition nodes through online estimation of an appropriate vigilance threshold. Empirical experiments compare the cluster validity and the learning efficiency of ART-C 2A with those of ART 2A, as well as three closely related clustering methods, namely online K-Means, batch K-Means, and SOM, in a quantitative manner. Besides retaining the online cluster creation capability of ART 2A, ART-C 2A gives the alternative clustering solution, which allows a direct control on the number of output …
Qos Routing Optimization Strategy Using Genetic Algorithm In Optical Fiber Communication Networks, Zhaoxia Wang, Zengqiang Chen, Zhuzhi Yuan
Qos Routing Optimization Strategy Using Genetic Algorithm In Optical Fiber Communication Networks, Zhaoxia Wang, Zengqiang Chen, Zhuzhi Yuan
Research Collection School Of Computing and Information Systems
This paper describes the routing problems in optical fiber networks, defines five constraints, induces and simplifies the evaluation function and fitness function, and proposes a routing approach based on the genetic algorithm, which includes an operator [OMO] to solve the QoS routing problem in optical fiber communication networks. The simulation results show that the proposed routing method by using this optimal maintain operator genetic algorithm (OMOGA) is superior to the common genetic algorithms (CGA). It not only is robust and efficient but also converges quickly and can be carried out simply, that makes it better than other complicated GA.
Capacitated Network Revenue Management Through Shadow Pricing, Mustapha Bouhtou, Madiagne Diallo, Laura Wynter
Capacitated Network Revenue Management Through Shadow Pricing, Mustapha Bouhtou, Madiagne Diallo, Laura Wynter
Research Collection School Of Computing and Information Systems
In this paper, we analyze a method that links Lagrange multipliers from a resource allocation problem to the problem of revenue or profit maximization. This technique, first proposed in the transportation science literature by [7] has important implications for telecommunication network pricing. Indeed, the framework provides a generalization of telecommunication resource allocation/shadow price-based schemes such as those of [6] and [9], in that it permits the optimization of the shadow prices themselves, through a computationally simple procedure. We analyze the extent to which revenue can be maximized on a network that uses shadow-price-based prices, and how to deal with cases …
Strategyproof Mechanisms For Ad Hoc Network Formation, C. Jason Woodard, David C. Parkes
Strategyproof Mechanisms For Ad Hoc Network Formation, C. Jason Woodard, David C. Parkes
Research Collection School Of Computing and Information Systems
Agents in a peer-to-peer system typically have incentives to influence its network structure, either to reduce their costs or increase their ability to capture value. The problem is compounded when agents can join and leave the system dynamically. This paper proposes three economic mechanisms that offset the incentives for strategic behavior and facilitate the formation of networks with desirable global properties.
On Quantitative Evaluation Of Clustering Systems, Ji He, Ah-Hwee Tan, Chew-Lim Tan, Sam-Yuan Sung
On Quantitative Evaluation Of Clustering Systems, Ji He, Ah-Hwee Tan, Chew-Lim Tan, Sam-Yuan Sung
Research Collection School Of Computing and Information Systems
Clustering refers to the task of partitioning unlabelled data into meaningful groups (clusters). It is a useful approach in data mining processes for identifying hidden patterns and revealing underlying knowledge from large data collections. The application areas of clustering, to name a few, include image segmentation, information retrieval, document classification, associate rule mining, web usage tracking, and transaction analysis.
Personalized Information Management For Web Intelligence, Ah-Hwee Tan
Personalized Information Management For Web Intelligence, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
Web intelligence can be defined as the process of scanning and tracking information on the World Wide Web so as to gain competitive advantages. This paper describes a system known as Flexible Organizer for Competitive Intelligence (FOCI) that transforms raw URLs returned by internet search engines into personalized information portfolios. FOCI builds information portfolios by gathering and organizing online information according to a user's needs and preferences. Through a novel method called User-Configurable Clustering, a user can personalize his/her portfolios in terms of the content as well as the information structure. The personalized portfolios can then be used to track …
Predictive Self-Organizing Networks For Text Categorization, Ah-Hwee Tan
Predictive Self-Organizing Networks For Text Categorization, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
This paper introduces a class of predictive self-organizing neural networks known as Adaptive Resonance Associative Map (ARAM) for classification of free-text documents. Whereas most sta- tistical approaches to text categorization derive classification knowledge based on training examples alone, ARAM performs supervised learn- ing and integrates user-defined classification knowledge in the form of IF-THEN rules. Through our experiments on the Reuters-21578 news database, we showed that ARAM performed reasonably well in mining categorization knowledge from sparse and high dimensional document feature space. In addition, ARAM predictive accuracy and learning efficiency can be improved by incorporating a set of rules derived from …
Supervised Adaptive Resonance Theory And Rules, Ah-Hwee Tan
Supervised Adaptive Resonance Theory And Rules, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
Supervised Adaptive Resonance Theory is a family of neural networks that performs incremental supervised learning of recognition categories (pattern classes) and multidimensional maps of both binary and analog patterns. This chapter highlights that the supervised ART architecture is compatible with IF-THEN rule-based symbolic representation. Specifically, the knowledge learned by a supervised ART system can be readily translated into rules for interpretation. Similarly, a priori domain knowledge in the form of IF-THEN rules can be converted into a supervised ART architecture. Not only does initializing networks with prior knowledge improve predictive accuracy and learning efficiency, the inserted symbolic knowledge can also …
Internet, World Wide Web, And Creativity, Keng Siau
Internet, World Wide Web, And Creativity, Keng Siau
Research Collection School Of Computing and Information Systems
The growth of the Internet has been the most astonishing technological and social phenomenon of the last decade of this century. In 1990 only a few academics had heard of it; now, more than 50 million people use it. By the turn of the century, that figure could be 100–200 million. So far, the network's only constant has been that the number of new users has doubled almost every 12–18 months. Most organizations have or will soon have Internet access. The popularity of Internet provides a tremendous opportunity for individuals and organizations to explore its features and services for electronic …
Cascade Artmap: Integrating Neural Computation And Symbolic Knowledge Processing, Ah-Hwee Tan
Cascade Artmap: Integrating Neural Computation And Symbolic Knowledge Processing, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
This paper introduces a hybrid system termed cascade adaptive resonance theory mapping (ARTMAP) that incorporates symbolic knowledge into neural-network learning and recognition. Cascade ARTMAP, a generalization of fuzzy ARTMAP, represents intermediate attributes and rule cascades of rule-based knowledge explicitly and performs multistep inferencing. A rule insertion algorithm translates if-then symbolic rules into cascade ARTMAP architecture. Besides that initializing networks with prior knowledge can improve predictive accuracy and learning efficiency, the inserted symbolic knowledge can be refined and enhanced by the cascade ARTMAP learning algorithm. By preserving symbolic rule form during learning, the rules extracted from cascade ARTMAP can be compared …
Inductive Neural Logic Network And The Scm Algorithm, Ah-Hwee Tan, Loo-Nin Teow
Inductive Neural Logic Network And The Scm Algorithm, Ah-Hwee Tan, Loo-Nin Teow
Research Collection School Of Computing and Information Systems
Neural Logic Network (NLN) is a class of neural network models that performs both pattern processing and logical inferencing. This article presents a procedure for NLN to learn multi-dimensional mapping of both binary and analog data. The procedure, known as the Supervised Clustering and Matching (SCM) algorithm, provides a means of inferring inductive knowledge from databases. In contrast to gradient descent error correction methods, pattern mapping is learned by an inductive NLN using fast and incremental clustering of input and output patterns. In addition, learning/encoding only takes place when both the input and output match criteria are satisfied in a …
Concept Hierarchy Memory Model: A Neural Architecture For Conceptual Knowledge Representation, Learning, And Commonsense Reasoning, Ah-Hwee Tan, Hui-Shin Vivien Soon
Concept Hierarchy Memory Model: A Neural Architecture For Conceptual Knowledge Representation, Learning, And Commonsense Reasoning, Ah-Hwee Tan, Hui-Shin Vivien Soon
Research Collection School Of Computing and Information Systems
This article introduces a neural network based cognitive architecture termed Concept Hierarchy Memory Model (CHMM) for conceptual knowledge representation and commonsense reasoning. CHMM is composed of two subnetworks: a Concept Formation Network (CFN), that acquires concepts based on their sensory representations; and a Concept Hierarchy Network (CHN), that encodes hierarchical relationships between concepts. Based on Adaptive Resonance Associative Map (ARAM), a supervised Adaptive Resonance Theory (ART) model, CHMM provides a systematic treatment for concept formation and organization of a concept hierarchy. Specifically, a concept can be learned by sampling activities across multiple sensory fields. By chunking relations between concepts as …
On The Use Of The Complexity Index As A Measure Of Complexity In Activity Networks, Bert De Reyck, Willy Herroelen
On The Use Of The Complexity Index As A Measure Of Complexity In Activity Networks, Bert De Reyck, Willy Herroelen
Research Collection Lee Kong Chian School Of Business
A large number of optimal and suboptimal procedures have been developed for solving combinatorial problems modeled as activity networks. The need to differentiate between easy and hard problem instances and the interest in isolating the fundamental factors that determine the computing effort required by these procedures, inspired a number of researchers to develop various complexity measures. In this paper we investigate the relation between the hardness of a problem instance and the topological structure of its underlying network, as measured by the complexity index. We demonstrate through a series of experiments that the complexity index, defined as the minimum number …
Adaptive Resonance Associative Map, Ah-Hwee Tan
Adaptive Resonance Associative Map, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
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 …
Fuzzy Neural Logic Network And Its Learning Algorithms, Fiona Fui-Hoon Nah, Nah Fiona
Fuzzy Neural Logic Network And Its Learning Algorithms, Fiona Fui-Hoon Nah, Nah Fiona
Research Collection School Of Computing and Information Systems
The paper introduces the basic features of fuzzy neural logic network. Each fuzzy neural logic network model is trained from a set of knowledge in the form of examples using one of the three learning algorithms introduced. These three learning algorithms are the delta rule controlled learning algorithm and two mathematical construction algorithms, namely, the local learning method and the global learning method. Once the fuzzy neural logic network model is constructed, it is ready to accept any unknown input from the user. With a low percentage of mismatched features, output solution can be obtained.