Knowledge Request-Broker Architecture: A Platform for Social Computational Intelligence
01 Jan 2010-
TL;DR: KnoRBA features a better way for heterogeneous agents to achieve mutual understanding: instead of specifying a protocol, it equips agents with programmatic means to provide knowledge to, and query it from the society.
Abstract: Computational systems and intelligent machines are facing with both compositional and environmental growing forms of complexity. We contribute a way to better deal with these forms of complexity by proposing a novel agent-based software platform: Knowledge request-Broker Architecture (KnoRBA). This solution aims at easily implementing self-organizing distributed software systems, mainly composed of socially interactive software agents. KnoRBA features a better way for heterogeneous agents to achieve mutual understanding: instead of specifying a protocol, it equips agents with programmatic means to provide knowledge to, and query it from the society. Utilization of KnoRBA is made possible by provision of appropriate language extensions and code libraries. This article, having reviewed the efficiencies and deficiencies of the existing literature, describes the basic principles, system architecture, and Java-based implementation of KnoRBA, as well as
Citations
More filters
Posted Content•
TL;DR: The Difference as discussed by the authors is a landmark book about how we think in groups and how our collective wisdom exceeds the sum of its parts, and how groups that display a range of perspectives outperform groups of like-minded experts.
Abstract: In this landmark book, Scott Page redefines the way we understand ourselves in relation to one another. The Difference is about how we think in groups--and how our collective wisdom exceeds the sum of its parts. Why can teams of people find better solutions than brilliant individuals working alone? And why are the best group decisions and predictions those that draw upon the very qualities that make each of us unique? The answers lie in diversity--not what we look like outside, but what we look like within, our distinct tools and abilities. The Difference reveals that progress and innovation may depend less on lone thinkers with enormous IQs than on diverse people working together and capitalizing on their individuality. Page shows how groups that display a range of perspectives outperform groups of like-minded experts. Diversity yields superior outcomes, and Page proves it using his own cutting-edge research. Moving beyond the politics that cloud standard debates about diversity, he explains why difference beats out homogeneity, whether you're talking about citizens in a democracy or scientists in the laboratory. He examines practical ways to apply diversity's logic to a host of problems, and along the way offers fascinating and surprising examples, from the redesign of the Chicago "El" to the truth about where we store our ketchup. Page changes the way we understand diversity--how to harness its untapped potential, how to understand and avoid its traps, and how we can leverage our differences for the benefit of all.
779 citations
TL;DR: The main aspects of AmI are identified through a review of the recent developments that have been achieved in these aspects and the problems yet to be solved and the visions of the future are pointed out.
Abstract: It has already been realized by the scientific and technical community that a new form of technology is going to lead the future technological developments. This technology will be more humancentric and will be more and more “hidden” within everyday-life objects. It will be smarter, personalized, pervasive and ubiquitous. This technology includes what is called Ambient Intelligence (AmI). In this paper, we identify the main aspects of AmI through a review of the recent developments that have been achieved in these aspects of AmI and Ambient Intelligence Environments (AmIEs), as well as point out the problems yet to be solved and the visions of the future.
4 citations
Cites background from "Knowledge Request-Broker Architectu..."
...These problems include mutual understanding between heterogeneous agents, a new architecture specification for general-purposed agents and their social system, as well as an Application Programming Interface for the development of social agent-based systems as referred in [50]....
[...]
23 Sep 2014
TL;DR: The theoretical aspect of A-Cell is introduced, its semantics and its design logic are introduced, and the progress made for its materialization is reported, including the A- Cell simulator, C/C++ runtime system, and precompiler.
Abstract: A-Cell is a high-level abstraction of fine-grained parallelism specifically designed to be applicable to all range of parallel devices from super computers based on CPUs or GPUs, to network of embedded devices. To achieve this, A-Cell adopts a programming model called "connectionist computing" and with that takes a leap step away from Turing programming model. Also, in contrast with most common solutions like PGAS that are holistic, the philosophy of A-Cell is reductionist. An ACell encapsulates a fine-grained task with its related variables. A source-to-source compiler translates the program to a set of programs that are compilable to the target devices. Execution of the task is through massive instantiation of an A-Cell prototype. The runtime system takes the responsibility of distributing A-Cell instances between all available nodes, cores or multiprocessors (MPs). The runtime system also assures synchronization and consistency between A-Cell instances. This paper introduces the theoretical aspect of A-Cell, its semantics and its design logic, and reports the progress made for its materialization, including the A-Cell simulator, C/C++ runtime system, and precompiler.
1 citations
06 Mar 2014
TL;DR: This extended abstract is an early introduction to the new revision of KnoRBA that makes it efficient in a domain like sensor networks where power and bandwidth are critical factors.
Abstract: Significant gap between software programming model and execution model is one major slowing factor in the development of the emerging field of Internet-of-Things. It is also one of the main reasons why software systems often lag behind hardware technologies and fail to capture the full potentials of modern day hardware infrastructure, which is mostly parallel and distributed. We need to change the way we think about software fundamentally, and make it, at its most basic level, to work like the physical world works: distributed, parallel, loosely connected, and asynchronous. KnoRBA achieves this by making the basic components of any program, such as a common word processor, to be asynchronous mobile agents. Then through provision of implementation and location transparency it establishes integration across a distributed environment. This extended abstract is an early introduction to the new revision of KnoRBA that makes it efficient in a domain like sensor networks where power and bandwidth are critical factors.
1 citations
Cites background from "Knowledge Request-Broker Architectu..."
...Let’s call the autonomous specialist entities mentioned above, agents, with “agent” being defined as (1) specialist, (2) stand-alone, (3) temporally continues, (4) autonomous, (5) reactive, (6) goal-oriented, (7) collaborative, and optionally (8) mobile software entity....
[...]
...The main job of ARE is (1) to route messages between agents, making the underlying communication mechanism transparent, and (2) to enforce security measures....
[...]
...What it takes to get to that point is to create a proper middleware that (1) enforces the decentralized distributed software design methodology, and (2) renders boundaries of machines, operating systems, and network environments, transparent....
[...]
Proceedings Article•
27 Oct 2011TL;DR: This paper describes a framework for this paradigm, and explains Social Regression an example of its practical implementation, and provides an overview on Knowledge-Request Broker Architecture, which is the platform made to support sociomimetic computing.
Abstract: Sociomimetic Computing, as described in this paper, is a computing paradigm inspired by social systems in which computer software is made out of socially cooperative agents as its basic components. To contrast with social simulation which is a computational method for analysis of social system, this paradigm is about synthesizing social systems for computational purposes. This paper describes a framework for this paradigm, and explains Social Regression an example of its practical implementation. It also provides an overview on Knowledge-Request Broker Architecture, which is the platform made to support sociomimetic computing. Being one of the first papers written on this paradigm, it also draws some trends for its future.
Cites background or methods from "Knowledge Request-Broker Architectu..."
...There are many agent-based programming solutions available, but none of them suit support sociomimetic computing for one reason or another (extensive discussion can be found in [3])....
[...]
...Implementation of Social Regression is made possible using Knowledge Request-Broker Architecture (KnoRBA) [3]....
[...]
References
More filters
Book•
[...]
TL;DR: Standard equipment thinking machines revenge of the nerds the mind's eye good ideas hotheads family values the meaning of life.
Abstract: Standard equipment thinking machines revenge of the nerds the mind's eye good ideas hotheads family values the meaning of life.
3,799 citations
Book•
[...]
01 Jan 1986
TL;DR: Marvin Minsky as discussed by the authors gave a revolutionary answer to the age-old question: "how does the mind work?" and showed that the mind does not work in a linear fashion.
Abstract: Marvin Minsky--one of the fathers of computer science and cofounder of the Artificial Intelligence Laboratory at MIT--gives a revolutionary answer to the age-old question: "how does the mind work?"
3,048 citations
"Knowledge Request-Broker Architectu..." refers background in this paper
...<string> ::= "’" <chars> "’" <chars> ::= [any character except "’"]* <numeric> ::= [-]? [1-9][0-9]* [....
[...]
...It is discussed by scientists like Minsky [7] and Page [14], that not a single solution but a combination of vast number of them can be the key to achieve a better level of intelligence....
[...]
...[0-9]+]? <name> ::= [a-z|A-Z][a-z|A-Z|0-9]+...
[...]
...The idea of social software initiated long ago since the Society of Mind [7] was proposed....
[...]
[...]
TL;DR: In this article, the authors describe the meaning of life as "standard equipment thinking machines revenge of the nerds the mind's eye good ideas good ideas hotheads family values the meaning" and describe a family with three children.
Abstract: Standard equipment thinking machines revenge of the nerds the mind's eye good ideas hotheads family values the meaning of life.
2,956 citations
TL;DR: The perceptual-motor modules, the goal module, and the declarative memory module are presented as examples of specialized systems in ACT-R, which consists of multiple modules that are integrated to produce coherent cognition.
Abstract: Adaptive control of thought–rational (ACT–R; J. R. Anderson & C. Lebiere, 1998) has evolved into a theory that consists of multiple modules but also explains how these modules are integrated to produce coherent cognition. The perceptual-motor modules, the goal module, and the declarative memory module are presented as examples of specialized systems in ACT–R. These modules are associated with distinct cortical regions. These modules place chunks in buffers where they can be detected by a production system that responds to patterns of information in the buffers. At any point in time, a single production rule is selected to respond to the current pattern. Subsymbolic processes serve to guide the selection of rules to fire as well as the internal operations of some modules. Much of learning involves tuning of these subsymbolic processes. A number of simple and complex empirical examples are described to illustrate how these modules function singly and in concert.
2,732 citations
"Knowledge Request-Broker Architectu..." refers background in this paper
...<string> ::= "’" <chars> "’" <chars> ::= [any character except "’"]* <numeric> ::= [-]? [1-9][0-9]* [....
[...]
...[0-9]+]? <name> ::= [a-z|A-Z][a-z|A-Z|0-9]+...
[...]
...Cognitive architectures like Soar [6] and ACT-R [5] are made for specific type of intelligence, and therefore they are almost useless when other types of intelligence needed, and more useless when combination of different types of intelligence is needed....
[...]
TL;DR: An Expectation-Maximization (EM) algorithm for adjusting the parameters of the tree-structured architecture for supervised learning and an on-line learning algorithm in which the parameters are updated incrementally.
Abstract: We present a tree-structured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are generalized linear models (GLIM's). Learning is treated as a maximum likelihood problem; in particular, we present an Expectation-Maximization (EM) algorithm for adjusting the parameters of the architecture. We also develop an on-line learning algorithm in which the parameters are updated incrementally. Comparative simulation results are presented in the robot dynamics domain.
2,418 citations
"Knowledge Request-Broker Architectu..." refers methods in this paper
...<string> ::= "’" <chars> "’" <chars> ::= [any character except "’"]* <numeric> ::= [-]? [1-9][0-9]* [....
[...]
...[0-9]+]? <name> ::= [a-z|A-Z][a-z|A-Z|0-9]+...
[...]
...To make a sense of comparison with HME (Hierarchical Mixture of Experts) [3], in figure 4....
[...]