Adaptive critics have shown much promise for designing optimal nonlinear controllers in an off-line context. Still, their greatest potential exists in the context Of reconfigurable control, that is, real time controll...
详细信息
Adaptive critics have shown much promise for designing optimal nonlinear controllers in an off-line context. Still, their greatest potential exists in the context Of reconfigurable control, that is, real time controller redesign in response to (substantial) changes in plant dynamics. To accomplish this, a framework is proposed for the application of adaptive critics in real-time control (for those critic methods requiring a model of the plant). The framework is presented in the context of work being done in reconfigurable flight control by the NW Computational Intelligence Lab (NWCIL) at Portland State University. The proposal incorporates recent work (by others) in fast and efficient on-line plant identification, considerations for bounding the computational costs of converging neural networks, and a novel approach (by us) toward the task of assuring system stability during the adaptation process. The potential and limitations of the proposed framework are discussed. It is suggested that with the recent rapid reduction in computational barriers, only certain theoretical issues remain as the central barriers to successful on-line application of the methods.
Intelligence Preparation of the Battlespace (IPB) is a predominantly "gray matter-based" fusion and information synthesis process conducted to predict possible future adversary courses of action. The purpose...
详细信息
We propose an efficient heuristic algorithm that sets up and releases lightpaths for connection requests dynamically. We partition the routing and wavelength assignment (commonly known as RWA) problem into two subprob...
详细信息
ISBN:
(纸本)0780374002
We propose an efficient heuristic algorithm that sets up and releases lightpaths for connection requests dynamically. We partition the routing and wavelength assignment (commonly known as RWA) problem into two subproblems and solves both of them using a well-known shortest path routing algorithm. For solving the routing subproblem, an auxiliary graph is created whereby the nodes and links in the original network are transformed to the edges and vertices, respectively, and the availability of each wavelength on the input and output links of a node as well as the number of available wavelength converters are taken into account in determining the weights of edges. Furthermore, for solving the wavelength assignment subproblem, an auxiliary graph is also utilized and the cost for wavelength conversion is taken into consideration in the edge weight function. A distinguished feature of our algorithm is that it employs more accurate network information on the availability of both the wavelengths and the wavelength converters than the existing algorithms in deciding the routing and the wavelength assignment. Simulation results show that our algorithm performs much better than previously proposed algorithms with comparable computation time, especially when the number of wavelengths is large while the number of converters at each node is limited.
A soft expert system is defined to be one that is qualitatively fuzzy. We present such a system known as KASER which stands for Knowledge Amplification by Structural Expert Randomization. KASER facilitates reasoning u...
详细信息
A soft expert system is defined to be one that is qualitatively fuzzy. We present such a system known as KASER which stands for Knowledge Amplification by Structural Expert Randomization. KASER facilitates reasoning using domain specific expert and commonsense knowledge. It accomplishes this through object-classed predicates and an associated novel inference engine. It addresses the high cost associated with the knowledge acquisition bottleneck. It also enables the entry of a basis of rules and provides for the automatic extension of that basis through domain symmetries. We demonstrate an application for KASER in the design of an intelligent tutoring system that teaches the basic science of crystal-laser design. It enables the student to experiment with various design concepts and receive feedback on the functionality of the proposed design. This is possible without a need to preprogram all possible scenarios.
A revision of Union College's Introduction to engineering and computer Science course is presented. The change include the introduction of a design project and competition, the presentation of engineering and comp...
详细信息
A revision of Union College's Introduction to engineering and computer Science course is presented. The change include the introduction of a design project and competition, the presentation of engineering and computer science concepts under a unifying theme, and the introduction of weekly talks from outside speakers. The course instruction also changed from a series of modules taught by different faculty to a structure in which all the faculty taught all the topics in the course. If this approach is used with a group of cooperative faculty, the benefits of the exposure to different teaching styles and understanding of other disciplines can be positive.
This work in traducest wo new unsupervised learning algorithms based on the WISARD weightless neural classifier model. The first one, the standard AUTOWISARD model, is able to perform fast one-shot, learning of unsort...
详细信息
An approach for systematically modifying the semantics of programming languages by semantics modifiers is described. Semantics modifiers are a class of programs that allow the development of general and reusable seman...
详细信息
Autism is a mental disorder characterized by deficits in socialization, communication, and imagination. Along with the deficits, autistic children may show savant skills ("islets of ability") of unknown orig...
详细信息
Autism is a mental disorder characterized by deficits in socialization, communication, and imagination. Along with the deficits, autistic children may show savant skills ("islets of ability") of unknown origin that puzzles their families and the psychologists. Comorbidity with epilepsy and mental retardation has brought the researchers' attention to neurobiological and cognitive theories of the syndrome. The present article proposes a neurobiological model for the autism based on the fundamental biological process of neuronal competition. A neural network capable of defining neural maps-synaptic projections preserving neighborhoods between two neural tissues-simulates the process of neurodevelopment. Experiments were performed reducing the level of neural growth factor released by the neurons, leading to ill-developed maps and suggesting the cause of the aberrant neurogenesis present in autism. The computer simulations hint that brain regions responsible for the formation of higher level representations are impaired in autistic patients. The lack of this integrated representation of the world would result in the peculiar cognitive deficits of socialization, communication, and imagination and could also explain some "islets of abilities", like excellent memory for raw data and stimuli discrimination. The neuronal model is based on plausible biological findings and on recently developed cognitive theories of autism. Close relations are established between the computational properties of the neural network model and the cognitive theory of autism denominated "weak central coherence", bringing some insight to the understanding of the disorder.
This paper addresses the problem of robust /spl Hscr//sub /spl infin// filtering for linear discrete-time systems subject to parameter uncertainties in the system state-space model and with multiple time delays in the...
详细信息
This paper addresses the problem of robust /spl Hscr//sub /spl infin// filtering for linear discrete-time systems subject to parameter uncertainties in the system state-space model and with multiple time delays in the state variables. The uncertain parameters are supposed to belong to a given convex bounded polyhedral domain. A methodology is developed to design a stable linear filter that assures asymptotic stability and a prescribed /spl Hscr//sub /spl infin// performance for the filtering error, irrespective of the uncertainty and the time delays. The proposed design is given in terms of linear matrix inequalities, which has the advantage in that it can be implemented numerically very efficiently.
We present the fuzzy Bayes predictor (FBP), a hybrid system for the task of monthly electric load forecasting. The FBP is a modification we introduce in the naive Bayes classifier in order to enable it to predict nume...
详细信息
ISBN:
(纸本)0780370449
We present the fuzzy Bayes predictor (FBP), a hybrid system for the task of monthly electric load forecasting. The FBP is a modification we introduce in the naive Bayes classifier in order to enable it to predict numerical values. We consider three versions of the FBP, each one with a different dependence among the input data: independence, first-order and second-order dependence. For verifying the efficiency of the FBP's prediction, we compare it with two fuzzy systems and two traditional forecasting methods, Box-Jenkins and Winters exponential smoothing.
暂无评论