Spelling suggestions: "subject:"[een] ARTIFICIAL INTELLIGENCE"" "subject:"[enn] ARTIFICIAL INTELLIGENCE""
71 |
Creating emotionally aware performance environments : a phenomenological exploration of inferred and invisible data spacePovall, Richard Mark January 2003 (has links)
The practical research undertaken for this thesis - the building of interactive and non-interactive environments for performance - posits a radical recasting of the performing body in physical and digital space. The choreographic and thematic context of the performance work has forced us', as makers, to ask questions about the nature of digital interactivity which in turn feeds the work theoretically, technically and thematically. A computer views (and attempts to interpret) motion information through a video camera, and, by way of a scripting language, converts that information into MIDI' data. As the research has developed, our company has been able to design environments which respond sensitivelyto particular artistic / performance demands. I propose to show in this research that is it possible to design an interactive system that is part of a phenomenological performance space, a mechanical system with an ontological heart. This represents a significant shift in thinking from existing systems, is at the heart of the research developments and is what I consider to be one of the primary outcomes of this research, outcomes that are original and contribute to the body of knowledge in this area. The phenomenal system allows me to use technology in a poetic way, where the poetic aesthetic is dominant - it responds to the phenomenal dancer, rather than merely to the 'physico-chemical' (Merleau-Ponty 1964 pp. 10-I I) dancer. Other artists whose work attempts phenomenological approaches to working with technology and the human body are referenced throughout the writing.
|
72 |
Various considerations on performance measures for a classification of ordinal dataNyongesa, Denis Barasa 13 August 2016 (has links)
<p> The technological advancement and the escalating interest in personalized medicine has resulted in increased ordinal classification problems. The most commonly used performance metrics for evaluating the effectiveness of a multi-class ordinal classifier include; predictive accuracy, Kendall's tau-b rank correlation, and the average mean absolute error (AMAE). These metrics are beneficial in the quest to classify multi-class ordinal data, but no single performance metric incorporates the misclassification cost. Recently, distance, which finds the optimal trade-off between the predictive accuracy and the misclassification cost was proposed as a cost-sensitive performance metric for ordinal data. This thesis proposes the criteria for variable selection and methods that accounts for minimum distance and improved accuracy, thereby providing a platform for a more comprehensive and comparative analysis of multiple ordinal classifiers. The strengths of our methodology are demonstrated through real data analysis of a colon cancer data set.</p>
|
73 |
An analysis of learning in weightless neural systemsBradshaw, Nicholas P. January 1997 (has links)
This thesis brings together two strands of neural networks research - weightless systems and statistical learning theory - in an attempt to understand better the learning and generalisation abilities of a class of pattern classifying machines. The machines under consideration are n-tuple classifiers. While their analysis falls outside the domain of more widespread neural networks methods the method has found considerable application since its first publication in 1959. The larger class of learning systems to which the n-tuple classifier belongs is known as the set of weightless or RAM-based systems, because of the fact that they store all their modifiable information in the nodes rather than as weights on the connections. The analytical tools used are those of statistical learning theory. Learning methods and machines are considered in terms of a formal learning problem which allows the precise definition of terms such as learning and generalisation (in this context). Results relating the empirical error of the machine on the training set, the number of training examples and the complexity of the machine (as measured by the Vapnik- Chervonenkis dimension) to the generalisation error are derived. In the thesis this theoretical framework is applied for the first time to weightless systems in general and to n-tuple classifiers in particular. Novel theoretical results are used to inspire the design of related learning machines and empirical tests are used to assess the power of these new machines. Also data-independent theoretical results are compared with data-dependent results to explain the apparent anomalies in the n-tuple classifier's behaviour. The thesis takes an original approach to the study of weightless networks, and one which gives new insights into their strengths as learning machines. It also allows a new family of learning machines to be introduced and a method for improving generalisation to be applied.
|
74 |
Rule extraction using destructive learning in artificial neural networksUnknown Date (has links)
The use of inductive learning to extract general rules from examples would be a promising way to overcome the knowledge acquisition bottleneck. Over the last decade, many such techniques have been proposed. None of these have proved to be the efficient, general rule-extractors for complex real-world applications. Recent research has indicated that some kinds of hybrid-learning techniques which integrate two or more learning strategies outperform single learning techniques. In designing such a hybrid-learning method, neural network learning can be expected to be a good partner because it is tolerant for noisy data and is very flexible for approximate data. / This dissertation proposes another such method--a rule extraction method using an artificial neural network (ANN) that is trained by destructive learning. Unlike other published methods, the method proposed here takes advantage of the smart (pruned) network which contains more exact knowledge regarding the problem domain (environment). The method consists of three phases: training, pruning, and rule-extracting. The training phase is concerned with ANN learning, using a general backpropagation (BP) learning algorithm. In the pruning phase, redundant hidden units and links are deleted from a trained network, and then, the link weights remaining in the network are retrained to obtain near-saturated outputs from hidden units. The rule extraction algorithm uses the pruned network to extract rules. / The proposed method is evaluated empirically on three application domains--the MONK's problems, the IRIS-classification data set, and the thyroid-disease diagnosis data set--and its performance is compared with that of other classification and/or machine learning methods. It is shown that for discrete samples, the proposed method outperforms others, while for continuous samples it can beat most other methods with which it is compared. The classifying accuracy of the proposed method is higher than that of either backpropagation learning or the pruned network on which it is based. / Source: Dissertation Abstracts International, Volume: 55-04, Section: B, page: 1526. / Major Professor: R. C. Lacher. / Thesis (Ph.D.)--The Florida State University, 1994.
|
75 |
Modified election methodology: A methodology for describing human beliefsUnknown Date (has links)
This dissertation presents Modified Election (or ME) methodology and shows how it may be used to describe the beliefs a human expert would form regarding the answer to a given question, based on the available evidence. For example, the methodology could be used to describe the beliefs a heart specialist would form, regarding the question whether a patient should be put on a low fat, low cholesterol diet, based on whether the patient is overweight, has a family history of heart problems, etc. ME methodology employs statistical methods used to interpret random samples, as well as the concept of a "Modified Election" which is developed in this dissertation. In ME methodology, the numbers of "votes" for the possible outcomes in a modified election are used to weight the different pieces of evidence which might affect an expert's beliefs. / Two other popular formalisms for describing beliefs are Bayesian theory and Dempster/Shafer theory. Certain problematic aspects of these two formalisms which motivated ME methodology are discussed. It is then shown how ME methodology overcomes these problems. ME methodology may be used as the basis for the design of expert systems. An expert system is presented which illustrates how to do this. / Source: Dissertation Abstracts International, Volume: 54-04, Section: B, page: 2068. / Major Professor: Daniel G. Schwartz. / Thesis (Ph.D.)--The Florida State University, 1993.
|
76 |
A cognitive hinting structure for deep domain knowledgeUnknown Date (has links)
A framework is presented for the acquisition of domain-specific knowledge from experts. This framework is referred to as the ENVIRONMENTAL HINTING (ENVHINT) framework. ENVHINT attempts to steer the expert's focus to the derivation of expert knowledge by embedding acquisition of expert knowledge in the dynamics of the environment which influenced expertise development. Within this framework, the research focuses on the development of cognitive structures which can be used to develop probing domain-specific questions. / Cognitive structures are developed from urban residents' repertory grids which are based on personal construct theory. A cognitive structure reveals dependencies in the form of construct equivalence classes and implications from one equivalence class to another. / Weights are assigned to the implication lines of a cognitive structure. They are obtained from a fuzzy grid, from which the cognitive structure is derived. The weights allow paths to be accessed according to relevancy of urban concerns. The relevancy strengths of paths are used to derive hinting domain-specific questions for experts. / Source: Dissertation Abstracts International, Volume: 54-04, Section: B, page: 2071. / Major Professor: Wyllis Bandler. / Thesis (Ph.D.)--The Florida State University, 1993.
|
77 |
FUZZY RELATIONAL DATA BASESUnknown Date (has links)
Much of human reasoning deals with imprecise, incomplete or vague information. However, the currently available commercial data base management systems handle only "exact" data items. Therefore, there is a need for an information system that allows representation and manipulation of imprecise information. Furthermore, it is desirable that an information system provides means for "individualization" of data to reflect the user's perception of data. / The proposed Fuzzy Relational Data Base (FRDB) model based on the research in the fields of relational data bases and theories of fuzzy sets and possibility is designed to satisfy the need for individualization and imprecise information processing. A commercial relational data base (RIM) is used as a host for the implementation of a FRDB system to demonstrate the feasibility of the model. / Source: Dissertation Abstracts International, Volume: 44-11, Section: B, page: 3460. / Thesis (Ph.D.)--The Florida State University, 1983.
|
78 |
Mimicking human language processing features using fuzzy syntax-semantics analyzer and semantic interpreterUnknown Date (has links)
The main aim of this dissertation has been to mimic natural language processing capabilities of human beings in a natural language processing system. The design and the development of the Syntax-Semantics analyzer (SS-analyzer) and the use of fuzzy in various language processing stages form the main crux of this dissertation. / The SS-analyzer is made up of two main modules: the syntax module and the semantics module. The SS-analyzer processes the input natural language sentences in an incremental fashion. The syntax and the semantics analyzer work in a coordinated manner to extract the meaning out of the input natural language sentences. This extracted meaning is then represented in a fuzzy relational representation structure. / The semantic interpreter complements the SS-analyzer in determining the meaning of input sentences when they are grammatically incorrect or do not make sense semantically. If the SS-analyzer is unable to determine the meaning of the input sentences, the semantic interpreter uses the contextual knowledge to determine the meaning. A prototype natural language processing system has been developed to test these theories. / Source: Dissertation Abstracts International, Volume: 53-09, Section: B, page: 4783. / Major Professor: L. J. Kohout. / Thesis (Ph.D.)--The Florida State University, 1992.
|
79 |
Intelligent fuzzy reasoning models with application to fuzzy controlUnknown Date (has links)
The successful application of fuzzy reasoning models to fuzzy control systems depends on a number of parameters, such as fuzzy membership functions, fuzzy implication operators, and the fuzzy relation matrix, that are usually decided upon subjectively by an expert operator. The purpose of this dissertation is to develop an intelligent fuzzy control system that combines fuzzy controller and learning mechanism in a hybrid system. Such hybrid system, which allows for imprecise information and/or uncertain environments, is imperative to the process of developing effective robust control systems for a large number of important real-time industrial processes. It is shown in this dissertation that the performance of fuzzy control systems can be improved considerably if the fuzzy reasoning model is supplemented by learning mechanisms. Two learning mechanisms are proposed in this research: one that uses genetic algorithms and the other is based on the utilization of neural networks. The genetic algorithm enables us to generate an optimal set of parameters for the fuzzy reasoning model based on their initial subjective selection. The exploitation of this initial selection, i.e., knowledge of the domain, by the genetic algorithm leads to an improved performance of the fuzzy controller. The neural-fuzzy reasoning model combines the computational paradigms of neural network and fuzzy rule-based reasoning in a hybrid system that also leads to an improved performance of the fuzzy control system. / Source: Dissertation Abstracts International, Volume: 53-07, Section: B, page: 3605. / Major Professor: Abraham Kandel. / Thesis (Ph.D.)--The Florida State University, 1992.
|
80 |
A Study on Semantic Relation Representations in Neural Word EmbeddingsUnknown Date (has links)
Neural network based word embeddings have demonstrated outstanding results in a variety of tasks, and become a standard input for Natural Language Processing (NLP) related deep learning methods. Despite these representations are able to capture semantic regularities in languages, some general questions, e.g., "what kinds of semantic relations do the embeddings represent?" and "how could the semantic relations be retrieved from an embedding?" are not clear and very little relevant work has been done. In this study, we propose a new approach to exploring the semantic relations represented in neural embeddings based on WordNet and Unified Medical Language System (UMLS). Our study demonstrates that neural embeddings do prefer some semantic relations and that the neural embeddings also represent diverse semantic relations. Our study also finds that the Named Entity Recognition (NER)-based phrase composition outperforms Word2phrase and the word variants do not affect the performance on analogy and semantic relation tasks. / A Thesis submitted to the Department of Computer Science in partial fulfillment of the requirements for the degree of Master of Science. / Summer Semester 2017. / July 17, 2017. / semantic relation, word2vec, word embedding, WordNet / Includes bibliographical references. / Xiuwen Liu, Professor Directing Thesis; Zhe He, Committee Member; Peixiang Zhao, Committee Member.
|
Page generated in 0.0457 seconds