Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (6876)
- Computer Sciences (6868)
- Databases and Information Systems (2875)
- Software Engineering (2164)
- Artificial Intelligence and Robotics (1253)
-
- Engineering (957)
- Numerical Analysis and Scientific Computing (844)
- Information Security (709)
- Graphics and Human Computer Interfaces (627)
- Social and Behavioral Sciences (570)
- Computer Engineering (512)
- Business (461)
- Operations Research, Systems Engineering and Industrial Engineering (418)
- Theory and Algorithms (387)
- Programming Languages and Compilers (333)
- OS and Networks (259)
- Communication (239)
- Social Media (194)
- Public Affairs, Public Policy and Public Administration (186)
- Data Storage Systems (176)
- Transportation (170)
- Education (152)
- Medicine and Health Sciences (140)
- Digital Communications and Networking (123)
- Management Information Systems (98)
- Computer and Systems Architecture (89)
- International and Area Studies (89)
- Asian Studies (88)
- Health Information Technology (83)
- Technology and Innovation (78)
- Keyword
-
- Deep learning (112)
- Machine learning (107)
- Social media (63)
- Data mining (59)
- Reinforcement learning (58)
-
- Artificial intelligence (55)
- Empirical study (55)
- Deep Learning (49)
- Software engineering (49)
- Optimization (47)
- Privacy (47)
- Task analysis (46)
- Cloud computing (45)
- Online learning (45)
- Visualization (45)
- Neural networks (44)
- Security (43)
- Training (43)
- Feature extraction (42)
- Anomaly detection (41)
- Collaboration (41)
- Singapore (41)
- Twitter (41)
- Large Language Models (36)
- Semantics (36)
- Android (35)
- Natural language processing (35)
- Classification (34)
- Machine Learning (33)
- Blockchain (32)
- Publication Year
- File Type
Articles 5941 - 5970 of 7017
Full-Text Articles in Entire DC Network
Bonus Plans Of Mice And Men, M. Thulasidas
Bonus Plans Of Mice And Men, M. Thulasidas
Research Collection School Of Computing and Information Systems
Our best-laid plans often go awry. We see it all the time at a personal level -- accidents (both good and bad), deaths (both of loved ones and rich uncles), births, and lotteries all conspire to reshuffle our priorities and render our plans null and void. In fact, there is nothing like a solid misfortune to get us to put things in perspective. This opportunity may be the proverbial silver lining we are constantly advised to see. What is true at a personal level holds true also at a larger scale. The industry-wide financial meltdown has imparted a philosophical clarity …
Creating Human-Like Autonomous Players In Real-Time First Person Shooter Computer Games, Di Wang, Budhitama Subagdja, Ah-Hwee Tan, Gee-Wah Ng
Creating Human-Like Autonomous Players In Real-Time First Person Shooter Computer Games, Di Wang, Budhitama Subagdja, Ah-Hwee Tan, Gee-Wah Ng
Research Collection School Of Computing and Information Systems
This paper illustrates how we create a software agent by employing FALCON, a self-organizing neural network that performs reinforcement learning, to play a well-known first person shooter computer game known as Unreal Tournament 2004. Through interacting with the game environment and its opponents, our agent learns in real-time without any human intervention. Our agent bot participated in the 2K Bot Prize competition, similar to the Turing test for intelligent agents, wherein human judges were tasked to identify whether their opponents in the game were human players or virtual agents. To perform well in the competition, an agent must act like …
Towards Expressive Specification And Efficient Model Checking, Jin Song Dong, Jun Sun
Towards Expressive Specification And Efficient Model Checking, Jin Song Dong, Jun Sun
Research Collection School Of Computing and Information Systems
System modeling is important and highly non-trivial. The choice of specification language is an important factor in the success of the entire development. The language should cover several facets of the requirements and the model should precisely capture (up to abstraction of irrelevant details) an existing system or a system to be built. The language should have a semantic model suitable to study the behaviors of the system and to establish the validity of desired properties. A formal model can be the basis for a variety of system development activities, e.g., system simulation, visualization, verification or prototype synthesis.
Integrating Specification And Programs For System Modeling And Verification, Jun Sun, Yang Liu, Jin Song Dong, Chunqing Chen
Integrating Specification And Programs For System Modeling And Verification, Jun Sun, Yang Liu, Jin Song Dong, Chunqing Chen
Research Collection School Of Computing and Information Systems
High level specification languages like CSP use mathematical objects as abstractions to represent systems and processes. System behaviors are described as process expressions combined with compositional operators, which are associated with elegant algebraic laws for system analysis. Nonetheless, modeling systems with non-trivial data and functional aspects using CSP remains difficult. In this work, we propose a modeling language named CSP# (short for communicating sequential programs) which integrates high-level modeling operators with low-level procedural codes, for the purpose of efficient mechanical system verification. We demonstrate that data operations can be modeled as terminating sequential programs, which can be composed using high-level …
Model Checking Linearizability Via Refinement, Yang Liu, Wei Chen, Yanhong A. Liu, Jun Sun
Model Checking Linearizability Via Refinement, Yang Liu, Wei Chen, Yanhong A. Liu, Jun Sun
Research Collection School Of Computing and Information Systems
Linearizability is an important correctness criterion for implementations of concurrent objects. Automatic checking of linearizability is challenging because it requires checking that 1) all executions of concurrent operations be serializable, and 2) the serialized executions be correct with respect to the sequential semantics. This paper describes a new method to automatically check linearizability based on refinement relations from abstract specifications to concrete implementations. Our method avoids the often difficult task of determining linearization points in implementations, but can also take advantage of linearization points if they are given. The method exploits model checking of finite state systems specified as concurrent …
Fair Model Checking With Process Counter Abstraction, Jun Sun, Yang Liu, Abhik Roychoudhury, Shanshan Liu, Jin Song Dong
Fair Model Checking With Process Counter Abstraction, Jun Sun, Yang Liu, Abhik Roychoudhury, Shanshan Liu, Jin Song Dong
Research Collection School Of Computing and Information Systems
Parameterized systems are characterized by the presence of a large (or even unbounded) number of behaviorally similar processes, and they often appear in distributed/concurrent systems. A common state space abstraction for checking parameterized systems involves not keeping track of process identifiers by grouping behaviorally similar processes. Such an abstraction, while useful, conflicts with the notion of fairness. Because process identifiers are lost in the abstraction, it is difficult to ensure fairness (in terms of progress in executions) among the processes. In this work, we study the problem of fair model checking with process counter abstraction. Even without maintaining the process …
Information Sharing And Strategic Signaling In Supply Chains, Robert J. Kauffman, Hamid Mohtadi
Information Sharing And Strategic Signaling In Supply Chains, Robert J. Kauffman, Hamid Mohtadi
Research Collection School Of Computing and Information Systems
Information sharing in procurement occurs in rich and varied industry contexts in which managerial decisions are made and organizational strategy is formulated. We explore how information sharing ought to work in procurement contexts that involve investments in inter-organizational information systems (IOS) and collaborative planning, forecasting and replenishment (CPFR) practices. How and under what circumstances does a firm that plays the role of a supply chain buyer decide to share information on key variables, such as point-of-sale consumer demand data with its supplier, up the supply chain? This is a key issue that crosses the boundary between supply chain management and …
Simplenpkl: Simple Non-Parametric Kernel Learning, Jinfeng Zhuang, Ivor Tsang, Steven C. H. Hoi
Simplenpkl: Simple Non-Parametric Kernel Learning, Jinfeng Zhuang, Ivor Tsang, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
Previous studies of Non-Parametric Kernel (NPK) learning usually reduce to solving some Semi-Definite Programming (SDP) problem by a standard SDP solver. However, time complexity of standard interior-point SDP solvers could be as high as O(n6.5). Such intensive computation cost prohibits NPK learning applicable to real applications, even for data sets of moderate size. In this paper, we propose an efficient approach to NPK learning from side information, referred to as SimpleNPKL, which can efficiently learn non-parametric kernels from large sets of pairwise constraints. In particular, we show that the proposed SimpleNPKL with linear loss has a closed-form solution that can …
Nonrigid Shape Recovery By Gaussian Process Regression, Jianke Zhu, Steven C. H. Hoi, Michael R. Liu
Nonrigid Shape Recovery By Gaussian Process Regression, Jianke Zhu, Steven C. H. Hoi, Michael R. Liu
Research Collection School Of Computing and Information Systems
Most state-of-the-art nonrigid shape recovery methods usually use explicit deformable mesh models to regularize surface deformation and constrain the search space. These triangulated mesh models heavily relying on the quadratic regularization term are difficult to accurately capture large deformations, such as severe bending. In this paper, we propose a novel Gaussian process regression approach to the nonrigid shape recovery problem, which does not require to involve a predefined triangulated mesh model. By taking advantage of our novel Gaussian process regression formulation together with a robust coarse-to-fine optimization scheme, the proposed method is fully automatic and is able to handle large …
Architectural Dualities In Complex Systems: Components, Interfaces, Technologies And Organizations, C. Jason Woodard, Joel West
Architectural Dualities In Complex Systems: Components, Interfaces, Technologies And Organizations, C. Jason Woodard, Joel West
Research Collection School Of Computing and Information Systems
Research on technological innovation and product development has long recognized the importance of product architecture, and many scholars have explored its relationship to the organizational structure of the product development process. Product architecture, in turn, has long encompassed both the allocation of functionality to components and the pattern of linkages between them. In this paper, we forge new connections among these established ideas by examining them as two pairs of dual relationships. First, we draw attention to the duality between components and interfaces. While innovation and product development researchers have historically emphasized the partitioning of products and systems into components, …
Mferio: The Design And Evaluation Of A Peer-To-Peer Mobile Payment System, Rajesh Krishna Balan, Narayanasamy Ramasubbu, Komsit Prakobphol, Nicolas Christin, Jason Hong
Mferio: The Design And Evaluation Of A Peer-To-Peer Mobile Payment System, Rajesh Krishna Balan, Narayanasamy Ramasubbu, Komsit Prakobphol, Nicolas Christin, Jason Hong
Research Collection School Of Computing and Information Systems
In this paper, we present the design and evaluation of a near-field communication-based mobile p2p payment application, called mFe-rio, that is designed to replace cash-based transactions. We first identify design criteria that payment systems should satisfy and then explain how mFerio, relative to those criteria, improves on the limitations of cash-based systems. We next describe mFerio's implementation and user interface design, focusing on the balance between usability and security. Finally, we present the results of a two-phase user study, involving a total of 104 people, that shows that mFerio has low cognitive load and is also fast, accurate, and easy …
Adaptive In-Network Processing For Bandwidth And Energy Constrained Mission-Oriented Multi-Hop Wireless Networks, Sharanya Eswaran, Matthew Johnson, Archan Misra, Thomas La Porta
Adaptive In-Network Processing For Bandwidth And Energy Constrained Mission-Oriented Multi-Hop Wireless Networks, Sharanya Eswaran, Matthew Johnson, Archan Misra, Thomas La Porta
Research Collection School Of Computing and Information Systems
In-network processing, involving operations such as filtering, compression and fusion, is widely used in sensor networks to reduce the communication overhead. In many tactical and stream-oriented wireless network applications, both link bandwidth and node energy are critically constrained resources and in-network processing itself imposes non-negligible computing cost. In this work, we have developed a unified and distributed closed-loop control framework that computes both a) the optimal level of sensor stream compression performed by a forwarding node, and b) the best set of nodes where the stream processing operators should be deployed. Our framework extends the Network Utility Maximization (NUM) paradigm, …
Non-Redundant Sequential Rules - Theory And Algorithm, David Lo, Siau-Cheng Khoo, Limsoon Wong
Non-Redundant Sequential Rules - Theory And Algorithm, David Lo, Siau-Cheng Khoo, Limsoon Wong
Research Collection School Of Computing and Information Systems
A sequential rule expresses a relationship between two series of events happening one after another. Sequential rules are potentially useful for analyzing data in sequential format, ranging from purchase histories, network logs and program execution traces. In this work, we investigate and propose a syntactic characterization of a non-redundant set of sequential rules built upon past work on compact set of representative patterns. A rule is redundant if it can be inferred from another rule having the same support and confidence. When using the set of mined rules as a composite filter, replacing a full set of rules with a …
Intentional Learning Agent Architecture, Budhitama Subagdja, Liz Sonenberg, Iyad Rahwan
Intentional Learning Agent Architecture, Budhitama Subagdja, Liz Sonenberg, Iyad Rahwan
Research Collection School Of Computing and Information Systems
Dealing with changing situations is a major issue in building agent systems. When the time is limited, knowledge is unreliable, and resources are scarce, the issue becomes more challenging. The BDI (Belief-Desire-Intention) agent architecture provides a model for building agents that addresses that issue. The model can be used to build intentional agents that are able to reason based on explicit mental attitudes, while behaving reactively in changing circumstances. However, despite the reactive and deliberative features, a classical BDI agent is not capable of learning. Plans as recipes that guide the activities of the agent are assumed to be static. …
A Formal Framework For Modeling And Validating Simulink Diagrams, Chunqing Chen, Jin Song Dong, Jun Sun
A Formal Framework For Modeling And Validating Simulink Diagrams, Chunqing Chen, Jin Song Dong, Jun Sun
Research Collection School Of Computing and Information Systems
Simulink has been widely used in industry to model and simulate embedded systems. With the increasing usage of embedded systems in real-time safety-critical situations, Simulink becomes deficient to analyze (timing) requirements with high-level assurance. In this article, we apply Timed Interval Calculus (TIC), a realtime specification language, to complement Simulink with TIC formal verification capability. We elaborately construct TIC library functions to model Simulink library blocks which are used to compose Simulink diagrams. Next, Simulink diagrams are automatically transformed into TIC models which preserve functional and timing aspects. Important requirements such as timing bounded liveness can be precisely specified in …
Sharing Hierarchical Mobile Multimedia Content Using The Mobitop System, Quang Minh Nguyen, Thi Nhu Quynh Kim, Dion Hoe-Lian Goh, Ee-Peng Lim, Yin-Leng Theng, Kalyani Chatterjea, Chew-Hung Chang, Aixin Sun, Khasfariyati Razikin
Sharing Hierarchical Mobile Multimedia Content Using The Mobitop System, Quang Minh Nguyen, Thi Nhu Quynh Kim, Dion Hoe-Lian Goh, Ee-Peng Lim, Yin-Leng Theng, Kalyani Chatterjea, Chew-Hung Chang, Aixin Sun, Khasfariyati Razikin
Research Collection School Of Computing and Information Systems
We introduce MobiTOP (Mobile Tagging of Objects and People), a map-based application which allows users to contribute and share geo-referenced multimedia annotations via mobile devices. An important feature of MobiTOP is that annotations are hierarchical, allowing annotations to be annotated to an arbitrary depth. MobiTOP's interface was designed using a participatory design methodology to ensure that the user interface meets the needs of potential users. In an evaluation, a group of student-teachers involved in a geographical field study were tasked to collaboratively identify rock formations using the MobiTOP system. The students who were in the field were guided by their …
Semisupervised Svm Batch Mode Active Learning With Applications To Image Retrieval, Steven C. H. Hoi, Rong Jin, Jianke Zhu, Michael R. Lyu
Semisupervised Svm Batch Mode Active Learning With Applications To Image Retrieval, Steven C. H. Hoi, Rong Jin, Jianke Zhu, Michael R. Lyu
Research Collection School Of Computing and Information Systems
Active learning has been shown as a key technique for improving content-based image retrieval (CBIR) performance. Among various methods, support vector machine (SVM) active learning is popular for its application to relevance feedback in CBIR. However, the regular SVM active learning has two main drawbacks when used for relevance feedback. First, SVM often suffers from learning with a small number of labeled examples, which is the case in relevance feedback. Second, SVM active learning usually does not take into account the redundancy among examples, and therefore could select multiple examples in relevance feedback that are similar (or even identical) to …
Zeros And Ones, M. Thulasidas
Zeros And Ones, M. Thulasidas
Research Collection School Of Computing and Information Systems
Computers are notorious for their infuriatingly literal obedience. I am sure anyone who has ever worked with a computer has come across the lack of empathy on its part – it follows our instructions to the dot, yet ends up accomplishing something altogether different from what we intend. Let’s spare a thought for the way your glorified adding machine makes sense of things
Distributed Constraint Optimization With Structured Resource Constraints, Akshat Kumar, Boi Faltings, Adrian Petcu
Distributed Constraint Optimization With Structured Resource Constraints, Akshat Kumar, Boi Faltings, Adrian Petcu
Research Collection School Of Computing and Information Systems
Distributed constraint optimization (DCOP) provides a framework for coordinated decision making by a team of agents. Often, during the decision making, capacity constraints on agents' resource consumption must be taken into account. To address such scenarios, an extension of DCOP-Resource Constrained DCOP - has been proposed. However, certain type of resources have an additional structure associated with them and exploiting it can result in more efficient algorithms than possible with a general framework. An example of these are distribution networks, where the flow of a commodity from sources to sinks is limited by the flow capacity of edges. We present …
Concernlines: A Timeline View Of Co-Occurring Concerns, Christoph Treude, Margaret-Anne Storey
Concernlines: A Timeline View Of Co-Occurring Concerns, Christoph Treude, Margaret-Anne Storey
Research Collection School Of Computing and Information Systems
Understanding the evolution of a software system requires understanding how information about the release history, non-functional requirements and project milestones relates to functional requirements on the software components. This short paper describes a new tool, called CONCERNLINES, that supports this cognitive process by visualizing co-occurring concerns over time.
A Novel Framework For Efficient Automated Singer Identification In Large Music Databases, Jialie Shen, John Shepherd, Bin Cui, Kian-Lee Tan
A Novel Framework For Efficient Automated Singer Identification In Large Music Databases, Jialie Shen, John Shepherd, Bin Cui, Kian-Lee Tan
Research Collection School Of Computing and Information Systems
Over the past decade, there has been explosive growth in the availability of multimedia data, particularly image, video, and music. Because of this, content-based music retrieval has attracted attention from the multimedia database and information retrieval communities. Content-based music retrieval requires us to be able to automatically identify particular characteristics of music data. One such characteristic, useful in a range of applications, is the identification of the singer in a musical piece. Unfortunately, existing approaches to this problem suffer from either low accuracy or poor scalability. In this article, we propose a novel scheme, called Hybrid Singer Identifier (HSI), for …
The Impact Of Process Choice In High Maturity Environments: An Empirical Analysis, Narayanasamy Ramasubbu, Rajesh Krishna Balan
The Impact Of Process Choice In High Maturity Environments: An Empirical Analysis, Narayanasamy Ramasubbu, Rajesh Krishna Balan
Research Collection School Of Computing and Information Systems
We present the results of a three year field study of the software development process choices made by project teams at two leading offshore vendors. In particular, we focus on the performance implications of project teams that chose to augment structured, plan-driven processes to implement the CMM level-5 Key Process Areas (KPAs) with agile methods. Our analysis of 112 software projects reveals that the decision to augment the firm-recommended, plan-driven approach with improvised, agile methods was significantly affected by the extent of client knowledge and involvement, newness of technology, and the project size. Furthermore this decision had a significant and …
Ss-Ids: Statistical Signature Based Ids, Payas Gupta, Chedy Raissi, Gerard Dray, Pascal Poncelet, Johan Brissaud
Ss-Ids: Statistical Signature Based Ids, Payas Gupta, Chedy Raissi, Gerard Dray, Pascal Poncelet, Johan Brissaud
Research Collection School Of Computing and Information Systems
Security of web servers has become a sensitive subject today. Prediction of normal and abnormal request is problematic due to large number of false alarms in many anomaly based Intrusion, Detection Systems(IDS). SS-IDS derives automatically the parameter profiles from the analyzed data thereby generating the Statistical Signatures. Statistical Signatures are based on modeling of normal requests and their distribution value without explicit intervention. Several attributes are used to calculate the behavior of the legitimate request on the web server. SS-IDS is best suited for the newly installed web servers which doesn't have low gene number of requests in. the data …
How Tagging Helps Bridge The Gap Between Social And Technical Aspects In Software Development, Christoph Treude, Margaret-Anne Storey
How Tagging Helps Bridge The Gap Between Social And Technical Aspects In Software Development, Christoph Treude, Margaret-Anne Storey
Research Collection School Of Computing and Information Systems
Empirical research on collaborative software development practices indicates that technical and social aspects of software development are often intertwined. The processes followed are tacit and constantly evolving, thus not all of them are amenable to formal tool support. In this paper, we explore how ldquotaggingrdquo, a lightweight social computing mechanism, is used to bridge the gap between technical and social aspects of managing work items. We present the results from an empirical study on how tagging has been adopted and adapted over the past two years of a large project with 175 developers. Our research shows that the tagging mechanism …
An Agent-Based Commodity Trading Simulation, Shih-Fen Cheng, Yee Pin Lim, Chao-Chi Liu
An Agent-Based Commodity Trading Simulation, Shih-Fen Cheng, Yee Pin Lim, Chao-Chi Liu
Research Collection School Of Computing and Information Systems
In recent years, the study of trading in electronic markets has received significant amount of attention, particularly in the areas of artificial intelligence and electronic commerce. With increasingly sophisticated technologies being applied in analyzing information and making decisions, fully autonomous software agents are expected to take up significant roles in many important fields. This trend is most obvious in the financial domain, where speed of reaction is highly valued and significant investments have been made in information and communication technologies.Despite the successes of automated trading in many important classes of financial markets, commodity trading has lagged behind, mainly because of …
Automatic Mining Of Functionally Equivalent Code Fragments Via Random Testing, Lingxiao Jiang, Zhendong Su
Automatic Mining Of Functionally Equivalent Code Fragments Via Random Testing, Lingxiao Jiang, Zhendong Su
Research Collection School Of Computing and Information Systems
Similar code may exist in large software projects due to some common software engineering practices, such as copying and pasting code and n-version programming. Although previous work has studied syntactic equivalence and small-scale, coarse-grained program-level and function-level semantic equivalence, it is not known whether significant fine-grained, code-level semantic duplications exist. Detecting such semantic equivalence is also desirable because it can enable many applications such as code understanding, maintenance, and optimization. In this paper, we introduce the first algorithm to automatically mine functionally equivalent code fragments of arbitrary size - down to an executable statement. Our notion of functional equivalence is …
Predicting Outcome For Collaborative Featured Article Nomination In Wikipedia, Meiqun Hu, Ee Peng Lim, Ramayya Krishnan
Predicting Outcome For Collaborative Featured Article Nomination In Wikipedia, Meiqun Hu, Ee Peng Lim, Ramayya Krishnan
Research Collection School Of Computing and Information Systems
In Wikipedia, good articles are wanted. While Wikipedia relies on collaborative effort from online volunteers for quality checking, the process of selecting top quality articles is time consuming. At present, the duty of decision making is shouldered by only a couple of administrators. Aiming to assist in the quality checking cycles so as to cope with the exponential growth of online contributions to Wikipedia, this work studies the task of predicting the outcome of featured article (FA) nominations. We analyze FA candidate (FAC) sessions collected over a period of 3.5 years, and examine the extent to which consensus has been …
On Mining Rating Dependencies In Online Collaborative Rating Networks, Hady W. Lauw, Ee Peng Lim, Ke Wang
On Mining Rating Dependencies In Online Collaborative Rating Networks, Hady W. Lauw, Ee Peng Lim, Ke Wang
Research Collection School Of Computing and Information Systems
The trend of social information processing sees e-commerce and social web applications increasingly relying on user-generated content, such as rating, to determine the quality of objects and to generate recommendations for users. In a rating system, a set of reviewers assign to a set of objects different types of scores based on specific evaluation criteria. In this paper, we seek to determine, for each reviewer and for each object, the dependency between scores on any two given criteria. A reviewer is said to have high dependency between a pair of criteria when his or her rating scores on objects based …
Classification Of Software Behaviors For Failure Detection: A Discriminative Pattern Mining Approach, David Lo, Hong Cheng, Jiawei Han, Siau-Cheng Khoo, Chengnian Sun
Classification Of Software Behaviors For Failure Detection: A Discriminative Pattern Mining Approach, David Lo, Hong Cheng, Jiawei Han, Siau-Cheng Khoo, Chengnian Sun
Research Collection School Of Computing and Information Systems
Software is a ubiquitous component of our daily life. We often depend on the correct working of software systems. Due to the difficulty and complexity of software systems, bugs and anomalies are prevalent. Bugs have caused billions of dollars loss, in addition to privacy and security threats. In this work, we address software reliability issues by proposing a novel method to classify software behaviors based on past history or runs. With the technique, it is possible to generalize past known errors and mistakes to capture failures and anomalies. Our technique first mines a set of discriminative features capturing repetitive series …
A Self-Organizing Neural Network Architecture For Intentional Planning Agents, Budhitama Subagdja, Ah-Hwee Tan
A Self-Organizing Neural Network Architecture For Intentional Planning Agents, Budhitama Subagdja, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
This paper presents a model of neural network embodiment of intentions and planning mechanisms for autonomous agents. The model bridges the dichotomy of symbolic and non-symbolic representation in developing agents. Some novel techniques are introduced that enables the neural network to process and manipulate sequential and hierarchical structures of information. It is suggested that by incorporating intentional agent model which relies on explicit symbolic description with self-organizing neural networks that are good at learning and recognizing patterns, the best from both sides can be exploited. This paper demonstrates that plans can be represented as weighted connections and reasoning processes can …