Artificial Intelligence + Distributed Systems = Agents

The concept of hierarchical reasoning system was introduced in [5], where an intuitive method to build such systems based on their inputs is given. In this paper we formalize several concepts which open a possible research line concerning the use of these structures. A hierarchical reasoning system H is a directed graph organized on several levels such that each node of the level j is a hyper-schema of order j. As a mathematical structure, H is an abstract one and a special kind of formal computation is introduced. As a result of this computation we obtain a set F(H) of formulas. We explain what we understand by an interpretation of H and define its corresponding semantical computation. By means of an interpretation I(H) for H and applying the rules of the semantical computation, each element of w ∈ F(H) becomes some object I(w) of a given space. We exemplify these concepts and we show that for two distinct interpretations I 1 (H) and I 2 (H) for the same system H, a given formula w ∈ F(H) is transformed into a sentence I 1 (w) of a natural language whereas I 2 (w) is a geometric image. A short description of a Java implementation of a hierarchical system generating images is also given in a separate section. By examples we show that the mechanism introduced in this paper allows us to model the distributed knowledge. Finally several open problems are specified.

“…We intend to develop the applications of an HDR system. First, we intend to use the mobile agents to process such systems ( [4]). Second, we intend to use the HDR systems in e-learning.…”

Section: Discussionmentioning

confidence: 99%

Hierarchical Distributed Reasoning System for Geometric Image Generation

Ţăndăreanu

Ghindeanu

Nicolescu³

2009

“…As early as in the early 1990s intensive studies have been conducted in recommender systems, and many scholars deem them as knowledge discovery in database (KDD) systems or electronic agent systems [12][13][14]. Up to now, the existing recommendation means can be generally classified as content based, collaborative, knowledge-based, demographic, and utility based [15][16][17], among which collaborative filtering based personalized recommendation is proved to be one of the most successfully used technology [15].…”

confidence: 99%

Study on Directed Trust Graph Based Recommendation for E-commerce System

Zhong

Zhang

Wang

et al. 2014

Automated recommender systems have played a more and more important role in marketing and ever increasingly booming e-commerce systems. They provide useful predictions personalized recommendations according to customers characteristics and a variety of large and complex product offerings. In many of these recommendation technologies Collaborative Filtering (CF) has proven to be one of the most successful recommendation method, which has been widely used in many e-commerce systems. The success of CF recommendation depends mainly on locating similar neighbors to get recommendation items. However, many scholars have found that the process of finding similar neighbors often fail, due to some inherent weaknesses of CF based recommendation. In view of this, we propose a trust feedback recommendation algorithm based on directed trust graph (DTG), which is able to propagate trust relationship. In our approach, there is no need to compute similarity between users, but utilize the trust relation between them to conduct prediction calculation. Based on the analysis of human trust perception, we incorporate the process into our recommendation algorithm. Experimental evaluation on real life Epinions datasets shows that the effectiveness and practicability of our approach.

“…They follow simple rules and there is no centralized control [9]. In swarm intelligence systems the focus is not on modelling, inspired from biologic (sub-symbolic) paradigms, but merely on simulating biologic behaviour [8].…”

Section: History and Related Workmentioning

confidence: 99%

Synthetic Genes for Artificial Ants. Diversity in Ant Colony Optimization Algorithms

Negulescu

Dzițac

Lascu

2010

Self Cite

Inspired from the fact that the real world ants from within a colony are not clones (although they may look alike, they are different from one another), in this paper, the authors are presenting an adapted ant colony optimisation (ACO) algorithm that incorporates methods and ideas from genetic algorithms (GA). Following the first (introductory) section of the paper is presented the history and the state of the art, beginning with the stigmergy and genetic concepts and ending with the latest ACO algorithm variants as multiagent systems (MAS). The rationale and the approach sections are aiming at presenting the problems with current stigmergy-based algorithms and at proposing a (possible -yet to be fully verified) solution to some of the problems ("synthetic genes" for artificial ants). A model used for validating the proposed solution is presented in the next section together with some preliminary simulation results. Some of the conclusions regarding the main subject of the paper (synthetic genes: agents within the MAS with different behaviours) that are closing the paper are: a) the convergence speed of the ACO algorithms can be improved using this approach; b) these "synthetic genes" can be easily implemented (as local variables or properties of the agents); c) the MAS is self-adapting to the specific problem that needs to be optimized.