In this study, an alternative seismic vulnerability assessment model is developed. For this purpose, one of the most popular artificial intelligence techniques, Artificial Neural Network (ANN), is used. Many ANN models are generated using 4 different network training functions, 1 to 50 hidden neurons and combination of structural parameters like number of stories, normalized redundancy scores, overhang ratios, soft story indices, normalized total column areas, normalized total wall areas are used to achieve the best assessment performance. Duzce database is used throughout the thesis for training ANN. A neural network simulator is developed in Microsoft Excel using the weights and parameters obtained from the best model created at Duzce damage database studies. Afyon, Erzincan, and Ceyhan databases are simulated using the developed simulator. A recently created database named Zeytinburnu is used for the projection purposes. The building sesimic vulnerability assessment of Zeytinburnu area is conducted on 3043 buildings using the proposed procedure.

Thesis (Ph. D.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Science, Department of Systems Science and Industrical Engineering, 2009. / Includes bibliographical references.

Fuzzy association rule mining discovers patterns in transactions, such as shopping baskets in a supermarket, or Web page accesses by a visitor to a Web site. Temporal patterns can be present in fuzzy association rules because the underlying process generating the data can be dynamic. However, existing solutions may not discover all interesting patterns because of a previously unrecognised problem that is revealed in this thesis. The contextual meaning of fuzzy association rules changes because of the dynamic feature of data. The static fuzzy representation and traditional search method are inadequate. The Genetic Iterative Temporal Fuzzy Association Rule Mining (GITFARM) framework solves the problem by utilising flexible fuzzy representations from a fuzzy rule-based system (FRBS). The combination of temporal, fuzzy and itemset space was simultaneously searched with a genetic algorithm (GA) to overcome the problem. The framework transforms the dataset to a graph for efficiently searching the dataset. A choice of model in fuzzy representation provides a trade-off in usage between an approximate and descriptive model. A method for verifying the solution to the hypothesised problem was presented. The proposed GA-based solution was compared with a traditional approach that uses an exhaustive search method. It was shown how the GA-based solution discovered rules that the traditional approach did not. This shows that simultaneously searching for rules and membership functions with a GA is a suitable solution for mining temporal fuzzy association rules. So, in practice, more knowledge can be discovered for making well-informed decisions that would otherwise be lost with a traditional approach.

This thesis investigates the functionality of the units used in connectionist Artificial Intelligence systems. Artificial Neural Networks form the foundation of the research and their units, Artificial Neurons, are first compared with alternative models. This initial work is mainly in the spatial-domain and introduces a new neural model, termed a Taylor Series neuron. This is designed to be flexible enough to assume most mathematical functions. The unit is based on Power Series theory and a specifically implemented Taylor Series neuron is demonstrated. These neurons are of particular usefulness in evolutionary networks as they allow the complexity to increase without adding units. Training is achieved via various traditiona and derived methods based on the Delta Rule, Backpropagation, Genetic Algorithms and associated evolutionary techniques. This new neural unit has been presented as a controllable and more highly functional alternative to previous models. The work on the Taylor Series neuron moved into time-domain behaviour and through the investigation of neural oscillators led to an examination of single-celled intelligence from which the later work developed. Connectionist approaches to Artificial Intelligence are almost always based on Artificial Neural Networks. However, another route towards Parallel Distributed Processing was introduced. This was inspired by the intelligence displayed by single-celled creatures called Protoctists (Protists). A new system based on networks of interacting proteins was introduced. These networks were tested in pattern-recognition and control tasks in the time-domain and proved more flexible than most neuron models. They were trained using a Genetic Algorithm and a derived Backpropagation Algorithm. Termed "Artificial BioChemical Networks" (ABN) they have been presented as an alternative approach to connectionist systems.

Thesis (doctoral)--Universität, Frankfurt am Main, 2006. / Includes bibliographical references and register.

Orientador: Secundino Soares Filho / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-06T08:33:44Z (GMT). No. of bitstreams: 1 PastorHumpiri_CarolinaJanet_M.pdf: 2093723 bytes, checksum: 2ef978811ccdca91867a3a47544e6581 (MD5) Previous issue date: 2005 / Resumo: O objetivo do Planejamento Energético da Operação de sistemas hidrotérmicos de geração é encontrar uma política operativa que forneça energia elétrica ao sistema, em um determinado período de planejamento, com confiabilidade e por um custo mínimo. Isto equivale a determinar um cronograma ótimo de geração para cada usina, a cada intervalo, de modo que o sistema atenda a demanda de forma confiável. Este trabalho faz uso de um dos paradigmas da Computação Evolutiva, as Estratégias Evolutivas (EEs), cuja característica principal é a auto-adaptação dos seus parâmetros durante o processo evolutivo, para a solução do problema de planejamento energético da operação. É feita uma comparação entre as abordagens por EEs e por Programação Não Linear baseada em Fluxo em Redes, para usinas do Sistema Elétrico Brasileiro. As EEs mostraram-se boas ferramentas para apurar a solução fornecida pela programação não linear devido ao elevado poder de exploração do espaço de soluções / Abstract: The objective of the energetic operation planning of hydrothermal generation systems is to find an operation policy that supplies electric energy to the system, during a given planning period, with reliability and by a minimum cost. This is equivalent determining an optimal scheduling of generation for each plant, at each interval, in such a way that the system load is attained with reliability. This work make use of one of the paradigms of Evolutionary Computation, Evolution Strategies (ES), whose main characteristic is the self-adaptation of its parameters during the evolution process, for the solution of the energetic operation planning. A comparison is performed for hydro plants of the Brazilian power system between the ES and the nonlinear network flow approaches. The ES approach turns to be a good tool to improve the solution obtained by the nonlinear programming approach due to its high potential to explore and exploit the solution space / Mestrado / Energia Eletrica / Mestre em Engenharia Elétrica

No description available.

<p>The agent technology represents one of the most consistent approaches to distributed artificial intelligence. Agents are characterized by autonomous, reactive, proactive, and social behavior.&nbsp;In addition, more complex, intelligent agents are often defined&nbsp;in terms of human-like mental attitudes, such as beliefs, desires,&nbsp;and intentions.</p><p>This thesis deals with software agents and multiagent systems&nbsp;in several ways. First, it defines a new reasoning architecture&nbsp;for intelligent agents called<em> Distributed Non-Axiomatic Reasoning System </em>(DNARS). Instead of the popular Belief-Intention-Desire model, it uses Non-Axiomatic Logic, a formalism developed for the domain of articial general intelligence. DNARS&nbsp;is highly-scalable, capable of answering questions and deriving&nbsp;new knowledge over large knowledge bases, while, at the same&nbsp;time, concurrently serving large numbers of external clients.&nbsp;</p><p>Secondly, the thesis proposes a novel agent runtime environment&nbsp;named<em> Siebog.</em> Based on the modern web and enterprise stan-dards, Siebog tries to reduce the gap between the agent technology and industrial applications. Like DNARS, Siebog is a&nbsp;distributed system. Its server side runs on computer clusters&nbsp;and provides advanced functionalities, such as automatic agent&nbsp;load-balancing and fault-tolerance. The client side, on the other<br />hand, runs inside web browsers, and supports a wide variety of&nbsp;hardware and software platforms.</p><p>Finally, Siebog depends on DNARS for deploying agents with&nbsp;unique reasoning capabilities.</p> / null / <p>Agentska tehnologija predstavlja dosledan pristup razvoju distribuirane ve&scaron;tačke&nbsp; inteligencije. Ono &scaron;to agente izdvaja od ostalih pristupa su autonomno, reaktivino,&nbsp; pro-aktivno, i socijalno pona&scaron;anje. Pored toga, kompleksniji, inteligentni agenti se često defini&scaron;u koristeći ljudske mentalne konstrukcije, kao sto su verovanja, želje i namere.</p><p>Disertacija se bavi softverskim agentima i multiagentskim sistemima sa nekoliko aspekata. Prvo, definisana je nova&nbsp; arhitektura za rasuđivanje sa primenom u razvoju&nbsp; inteligentnih agenata, nazvana Distribuirani sistem za ne-aksiomatsko rasuđivanje&nbsp; (eng. <em>Distributed Non-Axiomatic Reasoning System</em>) (DNARS). Umesto popularnog&nbsp;&nbsp; BDI modela za razvoj inteligentnih agenata (eng. <em>Belief-Desire-Intention</em>),&nbsp; arhitektura&nbsp; se zasniva na tzv. <em>ne-aksiomatskoj</em> logici, formalizmu razvijenom u domenu ve&scaron;tačke&nbsp; op&scaron;te inteligencije. DNARS je skalabilan softverski sistem, sposoban da odgovara na&nbsp;&nbsp; pitanja i da izvodi nove zaključke na osnovu veoma velikih&nbsp; baza znanja, služeći pri&nbsp;&nbsp; tome veliki broj klijenata.</p><p>Zatim, u disertaciji je predložena nova multiagentska platforma nazvana Siebog. Siebog je zasnovan na modernim standardima za razvoj veb aplikacija, čime poku&scaron;ava da smanji razliku izmedu multiagentskih sistema i sistema koji se koriste u&nbsp;industriji. Kao DNARS, i Siebog je distribuiran sistem. Na serverskoj strani, Siebog se izvr&scaron;ava na računarskim klasterima, pružajući napredne funkcionalnosti, poput automatske distribucije agenata i otpornosti na gre&scaron;ke. Sa klijentske strane, Siebog&nbsp;se izvr&scaron;ava u veb pretrazivačima i podržava &scaron;iroku lepezu hardverskih i softverskih platformi.</p><p>Konačno, Siebog se oslanja na DNARS za ravoj agenata sa jedinstvenim sposobnostima za rasuđivanje.</p>

1 Criminal liability of artificial intellingence Abstract The aim of this diploma thesis is to evaluate the possible criminal liability of artificial intelligence for its socially harmful unlawful conduct and if artificial intelligence cannot be criminal liable then evaluate criminal liability of persons for the unlawful acts of artificial intelligence, and also to assess whether it is necessary to change laws so that we can use in such situations the ultima ratio principle (criminal law). The first chapter deals with the concept of artificial intelligence. At the beginning of this chapter I deal with the definition of artificial intelligence from a technical point of view and I also deal with the most important points of its historical development. Then I analyze artificial intelligence from the perspective of the Czech legal order. First, I do so in connection with private law (specifically with civil law, respectively mainly with copyright) and then with public law (specifically with criminal law). The second chapter aims to introduce the concept of criminal liability as an institute of Czech law. I focus here on the individual components of criminal liability and its legal requirements, but not in an exhaustive way, but only to the extent that it is necessary to fulfill the topic of the thesis and to...

After a brief review of machine learning techniques and applications, this Ph.D. thesis examines several approaches for implementing machine learning architectures and algorithms into hardware within our laboratory. From this interdisciplinary background support, we have motivations for novel approaches that we intend to follow as an objective of innovative hardware implementations of dynamically self-reconfigurable logic for enhanced self-adaptive, self-(re)organizing and eventually self-assembling machine learning systems, while developing this new particular area of research. And after reviewing some relevant background of robotic control methods followed by most recent advanced cognitive controllers, this Ph.D. thesis suggests that amongst many well-known ways of designing operational technologies, the design methodologies of those leading-edge high-tech devices such as cognitive chips that may well lead to intelligent machines exhibiting conscious phenomena should crucially be restricted to extremely well defined constraints. Roboticists also need those as specifications to help decide upfront on otherwise infinitely free hardware/software design details. In addition and most importantly, we propose these specifications as methodological guidelines tightly related to ethics and the nowadays well-identified workings of the human body and of its psyche.