These are web resources that we believe are reasonably current (or of significant historical value) for software agent technology, including software agents, intelligent agents, intelligent software agents, autonomous agents, multi-agent systems (MAS), agent technology, agent-based computing, and topics in artificial intelligence and the Semantic Web that are deemed relevant to software agents.
I apologize for the fact that this list is in simple reverse chronological order (the order that I added to the list), but that's less work for me and does make it easier to find what's new. Ultimately the list should be a relational database that can be sorted by selected categories. Or maybe I should say that ultimately it should be embodied in a semantic web/grid that can be traversed by software agents to locate resources of interest.
Note: This list is now segmented by year since it became too long for Google to properly index!
[ Home | Blog | Books | Links | Glossary | Software Agent Manifesto | Pre-2001 | 2001 | 2002 | 2003 | 2004 | 2005 | 2006 ]
| Please let us know if you wish to add (or change) a link. Click here. |
Community Knowledge Sharing research at PARC - Research in this area explores technologies that can support community practices for sharing knowledge. Building on seminal PARC research on workplace communities and how they exchange knowledge, and drawing on competencies in computer and social sciences, researchers develop community-based knowledge-sharing technologies, tools, and systems. Their systems are based on extensive work practice studies in which they observe how people share knowledge and use technology to do their work. Researchers bring expertise in software architecture and ethno-methodology to bear in building community knowledge-sharing systems. Their design and deployment methods stand in contrast to hierarchical approaches in which workers are expected to adapt to new tools that are given to them by management.
- SmartWeb: Mobile Broadband Access to the Semantic Web - exploits the machine-understandable content of semantic Web pages for intelligent question-answering as a next step beyond today's search engines. Since semantically annotated Web pages are still very rare due to the time-consuming and costly manual markup, SmartWeb is using advanced language technology and information extraction methods for the automatic annotation of traditional web pages encoded in HTML or XML. But SmartWeb does not only deal with information-seeking dialogues but also with task-oriented dialogues, in which the user wants to perform a transaction via a Web service. SmartWeb is the follow-up project to SmartKom (www.smartkom.org), carried out from 1999 to 2003. SmartKom is a multimodal dialog system that combines speech, gesture, and facial expressions for input and output. Spontaneous speech under-standing is combined with the video-based recognition of natural gestures and facial expressions. The SmartKom architecture supports not only simple multimodal command-and-control interfaces, but also coherent and cooperative dialogues with mixed initiative and a synergistic use of multiple modalities. Although SmartKom works in multiple domains, it supports only restricted-domain question answering. SmartWeb goes beyond Smart-Kom in supporting open-domain question answering using the entire Web as its knowledge base. SmartWeb provides a context-aware user interface, so that it can support the user in different roles, e.g. as a car driver, a motor biker, a pedestrian or a sports spectator. SmartWeb is based on the Resource Description Framework (RDF/S) and the Web Ontology Language (OWL) for representing machine interpretable content on the Web. OWL-S ontologies support semantic service descriptions, focusing primarily on the formal specification of inputs, outputs, preconditions, and effects of Web services. In SmartWeb, multimodal user requests will not only lead to automatic Web service discovery and invocation, but also to the automatic composition, interoperation and execution monitoring of Web ser-vices.
- SEKT Project - develop and exploit the knowledge technologies which underlie Next Generation Knowledge Management. SEKT envisions knowledge workplaces where the boundaries between document management, content management, and knowledge management are broken down, and where knowledge management is an effortless part of day to day activities. Appropriate knowledge is automatically delivered to the right people at the right time at the right granularity via a range of user devices. Knowledge workers will be empowered to focus on their core roles and creativity; this is key to European competitiveness. The SEKT strategy is built around the synergy of the complementary know-how of the key European centres of excellence in Ontology and Metadata Technology, Knowledge Discovery and Human Language Technology, a leading commercial exponent of semantic technology, together with a major European ICT organisation.
- ATHENA (Advanced Technologies for interoperability of Heterogeneous Enterprise Networks and their Applications) - an Integrated Project sponsored by the European Commission in support of the Strategic Objective “Networked businesses and government” set out in the IST 2003-2004 Workprogramme of FP6. Building upon an ambitious Vision Statement “By 2010, enterprises will be able to seamlessly interoperate with others”, ATHENA aims to make a major contribution to interoperability by identifying and meeting a set of inter-related business, scientific & technical, and strategic objectives. The ATHENA programme of work is defined for producing results that span the full spectrum of interoperability from technology components to applications and services, from research & development to demonstration & testing, and from training to evaluation of technologies for societal impact. In ATHENA, Research and Development is executed in close synergy and collaboration with Community Building, for ensuring that solutions to multi-disciplinary research challenges are of optimal industrial relevance leading to broad uptake by the end user. One of the trends in the global market is the increasing collaboration among enterprises. Organisations are transforming themselves into “networked organisations” in order to increase their flexibility and reduce operational costs. They need to interact with a wide community of buyers, sellers and partners, and to adopt more dynamic trading and collaborative working practices. Enterprise systems and applications need to be interoperable in order to achieve seamless business interaction across organisational boundaries and thus realise networked organisations. Insufficient interoperability is a major impediment to the adoption of new business models that could enhance productivity and competitiveness, which is among the objectives of the Lisbon Strategy to modernise the European economy and to build a knowledge based economy in Europe. A significant part of the work carried out in ATHENA is dedicated to agent and peer-to-peer technologies with special interest how such technologies fit together with service-oriented architectures and the model-driven architecture proposed by OMG.
- Cognitive Machines Group, MIT Media Lab - goal is to create machines that learn to communicate in human-like ways by grasping the meaning of words in context and to understand how children learn language through computational models of situated language acquisition.
- The duality of knowledge by Paul M. Hildreth and Chris Kimble, October 2002 - Knowledge Management (KM) is a field that has attracted much attention both in academic and practitioner circles. Most KM projects appear to be primarily concerned with knowledge that can be quantified and can be captured, codified and stored - an approach more deserving of the label Information Management. Recently there has been recognition that some knowledge cannot be quantified and cannot be captured, codified or stored. However, the predominant approach to the management of this knowledge remains to try to convert it to a form that can be handled using the 'traditional' approach. This paper argues that this approach is flawed and some knowledge simply cannot be captured. A method is needed which recognizes that knowledge resides in people: not in machines or documents. This paper argues that KM is essentially about people and the earlier technology driven approaches, which failed to consider this, were bound to be limited in their success. One possible way forward is offered by Communities of Practice, which provide an environment for people to develop knowledge through interaction with others in an environment where knowledge is created nurtured and sustained.
- Icosystem Corporation - applies its expertise in complex adaptive systems to identify opportunities in an economic network and design strategies that have a high probability of realizing those opportunities. Complex adaptive systems encompass biological systems as well as many business systems. Icosystem views a market as a commercial ecosystem consisting of consumers and competing businesses - a number of agents playing different roles according to a variety of rules. The behavior of customers and competitors, as well as the impact of environmental conditions, all have a significant impact on the success and trajectory of an individual organization. Icosystem applies its core capabilities in key components of complexity science to create reality-based models that can easily be manipulated and reconfigured to explore changing scenarios and analyze the impact of various strategies. Icosystem's application of its core technology typically consists of three phases: 1) Replication: through agent-based modeling, Icosystem creates a model of a particular business environment that closely mirrors the real world, 2) Exploration: once the model is built, Icosystem explores multiple combinations of strategic levers and actions, identifying those that appear to lead to the desired results, and 3) Exploitation: after a range of strategic options is identified, Icosystem conducts robustness analysis exploring how the outcomes of these solutions may be impacted by changes in the business ecosystem.
- Is There an Intelligent Agent in Your Future? - classic article on intelligent internet agents by Prof. James Hendler in Nature, vintage 1999, in which he tells us "The area of agent-based systems is a hot one. We have the technology to build software agents that are communicative, capable, autonomous and adaptive – the key behaviours needed to help make our internet journeys more fruitful. The limiting factors in building such systems are being overcome, and new approaches are emerging from information technology research laboratories around the world. In short, if you're not now using agent-based technology, don't worry, you soon will be."
- Scripting for the Semantic Web - Scripting languages such as Python, PHP, Perl, JavaScript, Ruby, ASP, JSP and ActionScript are playing a central role in current development towards flexible, lightweight web applications following the AJAX and REST design paradigms. These languages are the tools of a generation of web programmers who use them to quickly create server and client-side web applications. Scripting languages are lightweight and easy to learn, but on the other hand mature enough to be used within complex applications. Many deployed Semantic Web applications from the wiki, blog, FOAF, and RSS communities, as well as many innovative mashups from the Web 2.0 and Open Data movements are using scripting languages and it is likely that the process of RDF-izing existing database-backed websites, wikis, blogs and content management systems will largely rely on scripting languages.
- Karl-Erik Sveiby's online library for Knowledge Management - an interesting collection of papers on various topics related to knowledge management.
- OIL & UPML: A Unifying Framework for the Knowledge Web by D. Fensel, M. Crubezy, F. van Harmelen, and I. Horrocks - a paper which discusses the Ontology Inference Layer (OIL) that was proposed as a description language for ontology interchange (designed for specifying static information) and UPML, which is being developed for describing reasoning components. UPML helps to automatically configure scattered reasoning components that can be used as inference services via networks. Integrating these two description types is a necessary step toward a knowledge web, where the distinction between static and dynamic information sources will become transparent for the user. The main contribution of the paper is the comparison of these approaches.
- Knowledge Management and Decision Support (KMDS) Website from U.S. Navy SPAWAR Systems Center - efforts to explore advanced technologies for collaboration and knowledge transaction, augmented cognition, knowledge webs, tactical decision making under stress, and decision support systems.
- Knowledge Web (K-Web) from U.S. Navy SPAWAR Systems Center - project to increase speed of command using Web-enabled technologies. Knowledge Web (K-Web) PDF, Knowledge Web (K-Web) PowerPoint.
- The Knowledge Web by Sumathi Gopall - a paper is based on the masters thesis "Aristotle and the Knowledge Web" [1]. The Knowledge Web was motivated by the development of an online classroom called Aristotle for a Biology course of Rutgers university. Aristotle is built using HTML and JavaScript and it presents the course by dividing it into lectures. The lecture web pages contain hyperlinks to topics and keywords. Although this method is fairly effective in conveying course content, it does not portray logical relationships between topics and keywords. It also lacks interactivity that comes from a teacher in a conventional classroom. This paper describes the design and implementation of The Knowledge Web which overcomes the above mentioned shortcomings. It graphically portrays concepts and topics. It presents an integrated view of the multitude of information available pertaining to a certain topic. The information may be in different multimedia formats. The Knowledge Web differs from traditional schemes of Knowledge Representation, as it does not deal with assimilation and construction of a knowledge domain. The Knowledge Web assumes that pieces of information already exist, and they have been categorized into separate topics. On the other hand, representation of topics and their relationships in a knowledge web is similar to the representation of objects and their associations in Cognitive Maps. The knowledge web representation is close to the way information is represented in a human mind. Thus The Knowledge Web aids in meta-cognition. Two applications have been designed and implemented to construct and navigate through knowledge webs. These are : The Knowledge Web Composer to construct knowledge webs and the Knowledge Web Navigator to view and browse through knowledge webs. A prototype of the Knowledge Web has been implemented.
- Cougaar Software, Inc. - a privately held company that provides intelligent technology solutions, software and related services to commercial and military sectors. The company was formed in 2001 to transition a powerful suite of advanced technologies from military research to the commercial market. Through this work and subsequent military transitions, they have matured and proven this technology, the Defense Advanced Research Project Agency's (DARPA) Cognitive Agent Architecture (Cougaar) in various secure, time-critical operational environments. Their resulting solutions represent some of the most advanced reasoning and intelligent automation capabilities in existence.
- ActiveEdge® Middleware from Cougaar Software - an intelligent agent-based middleware platform for building complex, distributed, intelligent applications. ActiveEdge is designed to transform data into usable knowledge and give active visibility into enterprise operations. ActiveEdge is a dynamic and adaptive sensor-enabled, middleware software platform. It collects data from a wide variety of distributed data sources and models including systems, software, and sensor hardware such as RFID and bar codes, cyber intrusion detection systems, temperature control sensors, etc. It then turns this data into intelligent and actionable business information and integrates effortlessly back into enterprise applications such as ERP, Supply Chain Management, Transportation Management, Warehouse Management, Facilities Management, to name a few. The overall purpose of ActiveEdge is to allow enterprises to create an operational understanding of events as applied to their business context, detect emerging trends and then react to these trends in an accurate and time-critical manner. ActiveEdge creates an understandable real-time picture of enterprise operations and provides execution monitoring and collaborative decision support. To enable users to perform with advanced focus and clarity in their unique environments, event triggers, alerts, information analysis, and reporting are fully customizable. Ultimately, ActiveEdge empowers organizations to be agile, adaptive, and flexible.
- "ARISTOTLE" (THE KNOWLEDGE WEB) by W. Daniel Hillis on John Brockman's Edge - With the knowledge web, humanity's accumulated store of information will become more accessible, more manageable, and more useful. Anyone who wants to learn will be able to find the best and the most meaningful explanations of what they want to know. Anyone with something to teach will have a way to reach those who what to learn. Teachers will move beyond their present role as dispensers of information and become guides, mentors, facilitators, and authors. The knowledge web will make us all smarter. The knowledge web is an idea whose time has come.
- Transversal Memory Engine - enables computers to store and recall information by relating concepts — like human memory. The Memory Engine starts with a generic understanding of how things are related. For example, it ‘knows’ that an apple is a type of fruit that grows on trees. Due to this rich baseline knowledge, Transversal’s solutions are able to understand and answer complex questions. As more knowledge is added to the knowledgebase the Memory Engine adapts its relationships, and will quickly learn (for example) that an Apple can also be a type of computer. Transversal’s Memory Engine is the result of research and development by top researchers in Information Theory and Machine Learning from Caltech and Cambridge universities. Transversal co-founder, Prof. David MacKay, is a world renowned expert in Artificial Intelligence. He pioneered Bayesian Neural Networks in the late 1980s and remains at the forefront of the field.
- A Survey of Cognitive and Agent Architectures (Univ. of Michigan) - some rational, structured access to an analysis of cognitive and agent architectures. Twelve architectures have been used for a preliminary analysis representing a wide range of current architectures in artificial intelligence (AI). The aim of the project is to facilitate both an understanding of current architectures and provide insight to the development of future, improved intelligent agent architectures. This work was based on publications from 1992 and earlier.
- GAIA - a methodology for agent-oriented analysis and design developer by Prof. Nick Jennings, et al. This is one of the first methodologies that has been specifically developed for agent-based systems.
FRODO ("A Framework for Distributed Organizational Memories") - a project focused on methods and tools for building and maintaining Distributed Organizational Memories (DOMs) in a real-world enterprise environment. It is a successor project of the DFKI KnowMore and VirtualOffice projects. The technical approach is based upon an application-driven combination of techniques from: agents for workflow enactment and information access, ontology acquisition from texts and user interaction, and document analysis and understanding.
- Magenta Technology - builds commercially viable technology based upon the concept of Multi-Agent Systems. They develop next generation solutions and services through 3 main activities: 1) Supply Chain Execution and Logistics Components: Network Scheduler and Network Designer, 2) Magenta Technology Platform: Engines, Toolsets and Knowledge Engineering Resources to extend the existing products or to use as a base for building custom applications, and 3) Licensing Intellectual Property for industrial use. Magenta's products and services are based on multi-agent and semantic web technologies. They are designed to allow businesses to make better decisions faster. Multi-agents drive the decision making process using real time data and then make decisions working within the enterprise knowledge base which holds all specific business decision criteria. Their products and services are designed to deal with highly complex business situations which are beyond of the capabilities of existing software.
- i-Schedulers from Magenta Technology - intelligent, event-driven planning software that helps business executives, managers and operation staff to make better decisions faster. i-Scheduler has been designed to provide high-transaction, complex business networks with the agile, responsive and robust decision-making support required to allocate business resources in near real-time, dynamic conditions. Magenta's i-Schedulers harness the power of multi-agent and semantic web technologies to enable faster decision-making that drives more competitive supply chains.
- SemTech 2006 - 2006 Semantic Technology Conference - where customers, developers and researchers converge to discuss the commercialization of Semantic Technologies. It’s also your fast track to learning what Semantic Technologies are all about, and how to exploit them in your organization.
- Project10X - a research, education, and consulting initiative organized by Mills Davis that champions high-performance business practices, integrated processes, and “smart” technologies such as semantic knowledge technologies. Project10X helps businesses improve profitability through process innovation, appropriate technology investment, and strategic partnerships. Benefits to their clients include major cost reduction and cycle time improvement in mission critical workflow, added value for customers, low capital investment, rapid ROI, and greatly reduced risk.
- The Bootstrap Institute - conceived by Dr. Douglas C. Engelbart to further his lifelong career goal of boosting individual and organizational ability to better address problems that are complex and urgent. Doug's rationale is that our world is a complex place with urgent problems of a global scale, the rate, scale, and complex nature of change is unprecedented and beyond the capability of any one person, organization, or even nation to comprehend and respond to, challenges of an exponential scale require an evolutionary coping strategy of a commensurate scale at a cooperative cross-disciplinary, international, cross-cultural level, we need a new, co-evolutionary environment capable of handling simultaneous complex social, technical, and economic changes at an appropriate rate and scale, the grand challenge is to boost the collective IQ of organizations and of society, a successful effort brings about an improved capacity for addressing any other grand challenge, the improvements gained and applied in their own pursuit will accelerate the improvement of collective IQ (the bootstrapping strategy), and those organizations, communities, institutions, and nations that successfully bootstrap their collective IQ will achieve the highest levels of performance and success. The Institute's mission is to: promote awareness of the scale, urgency, and complexity of the challenges we face, catalyze, launch, and shepherd an active, strategic pursuit of boosting the collective IQ on a scale commensurate with the rate, scale, and pervasiveness of change, create an exploratory environment where participants can collaborate, experiment, and set in motion advanced pilot outposts in diverse application areas, enable a whole new way of thinking about the way we work, learn, and live together, promote development of a collective IQ among, within, and by networked improvement communities, cultivate a knowledge environment that includes a shared dynamic knowledge repository (DKR), foster development of an open-platform information system infrastructure based on an open hyperdocument systems (OHS) framework, share the A-B-C's of bootstrapping and support co-evolution of human organizations and their tools, enable sharing of effort, cost and risks of advanced exploration among a diverse set of organizations and improvement communities, and push the scaling of bootstrapping toward what could become national improvement infrastructures, as well as a global improvement infrastructure.
- Introduction to Quantum Computing by Andrew Steane, Oxford University - relates to the re-investigation of the fundamental principles of physics from the standpoint of information theory.
- Smart Spaces (CSIRO) - a network of embedded devices that creates an adaptive infrastructure that reacts continuously and intelligently to a vast quantity of data. This intelligent reaction is mediated by autonomous agents which work together in a common open environment, combining individual strategies into overall behaviour. Without centralised controllers, agents are expected to self-organise and survive on the basis of local, rather than global, information. Multi-agent interactions lead to "emergent" patterns in overall system behaviour which is not reducible to, or not easily predictable from, individual agents' actions.
[ Home | Blog | Books | Links | Glossary | Software Agent Manifesto | Pre-2001 | 2001 | 2002 | 2003 | 2004 | 2005 | 2006 ]
Updated: March 19, 2006 11:58:58 AM -0500
Copyright © 2006 John W. Krupansky d/b/a Base Technology