51 |
Modélisation supervisée de données fonctionnelles par perceptron multi-couchesConan-Guez, Brieuc 18 December 2002 (has links) (PDF)
L'Analyse de Données Fonctionnelles est une extension de l'analyse de données traditionnelles à des individus décrits par des fonctions. Le travail présenté ici s'inscrit pleinement dans ce courant, et tente de faire la jonction entre le domaine de la statistique fonctionnelle, et celui des techniques "neuronales" classiques. L'extension du perceptron multi-couches (PMC) à des espaces fonctionnels, proposé dans ce travail, apporte une réponse naturelle au traitement d'individus de type fonctions. Deux approches distinctes sont ici présentées : une approche par traitement direct des fonctions d'entrée et une approche par projection sur une base topologique de l'espace fonctionnel considéré (méthode classique en Analyse de Données Fonctionnelles). Pour chacune de ces deux méthodes, on montre dans un premier temps que le modèle est un approximateur universel, i.e. que toute fonction continue définie sur un compact d'un espace fonctionnel peut être approchée arbitrairement bien par un PMC fonctionnel. Dans un deuxième temps, on s'intéresse aux propriétés de consistance de l'estimateur fonctionnel. L'originalité de ce résultat vient du fait que non seulement l'estimation s'effectue sur un nombre fini d'individus (les fonctions observées), mais que de plus chacune de ces fonctions n'est connue qu'en un nombre fini de points d'observation (discrétisation). Un point important à noter est que ce résultat s'appuie sur une modélisation aléatoire du design des fonctions d'entrée. Enfin, on montre que le modèle peut encore être adapté afin d'obtenir une réponse fonctionnelle, ce qui autorise le traitement de processus fonctionnels à temps discret. L'approximation universelle et la consistance de l'estimateur (dans le cas i.i.d) sont encore vérifiées.
|
52 |
Spectral Pattern Recognition by a Two-Layer Perceptron: Effects of Training Set SizeFischer, Manfred M., Staufer-Steinnocher, Petra 10 1900 (has links) (PDF)
Pattern recognition in urban areas is one of the most challenging issues in
classifying satellite remote sensing data. Parametric pixel-by-pixel classification
algorithms tend to perform poorly in this context. This is because urban areas
comprise a complex spatial assemblage of disparate land cover types - including
built structures, numerous vegetation types, bare soil and water bodies. Thus,
there is a need for more powerful spectral pattern recognition techniques,
utilizing pixel-by-pixel spectral information as the basis for automated urban
land cover detection. This paper adopts the multi-layer perceptron classifier
suggested and implemented in [5]. The objective of this study is to analyse the
performance and stability of this classifier - trained and tested for supervised
classification (8 a priori given land use classes) of a Landsat-5 TM image
(270 x 360 pixels) from the city of Vienna and its northern surroundings
- along with varying the training data set in the single-training-site case.
The performance is measured in terms of total classification, map user's and
map producer's accuracies. In addition, the stability with initial parameter
conditions, classification error matrices, and error curves are analysed in some
detail. (authors' abstract) / Series: Discussion Papers of the Institute for Economic Geography and GIScience
|
53 |
Computational and storage based power and performance optimizations for highly accurate branch predictors relying on neural networksAasaraai, Kaveh 09 August 2007 (has links)
In recent years, highly accurate branch predictors have been proposed primarily for high performance processors. Unfortunately such predictors are extremely energy consuming and in some cases not practical as they come with excessive prediction latency. Perceptron and O-GEHL are two examples of such predictors. To achieve high accuracy, these predictors rely on large tables and extensive computations and require high energy and long prediction delay. In this thesis we propose power optimization techniques that aim at reducing both computational complexity and storage size for these predictors. We show that by eliminating unnecessary data from computations, we can reduce both predictor's energy consumption and prediction latency. Moreover, we apply information theory findings to remove noneffective
storage used by O-GEHL, without any significant accuracy penalty. We reduce the dynamic and static power dissipated in the computational parts of the predictors. Meantime we improve performance as we make faster prediction possible.
|
54 |
Developing basic soccer skills using reinforcement learning for the RoboCup small size leagueYoon, Moonyoung 03 1900 (has links)
Thesis (MSc)--Stellenbosch University, 2015. / ENGLISH ABSTRACT: This study has started as part of a research project at Stellenbosch University
(SU) that aims at building a team of soccer-playing robots for the
RoboCup Small Size League (SSL). In the RoboCup SSL the Decision-
Making Module (DMM) plays an important role for it makes all decisions
for the robots in the team. This research focuses on the development of
some parts of the DMM for the team at SU.
A literature study showed that the DMM is typically developed in a
hierarchical structure where basic soccer skills form the fundamental building
blocks and high-level team behaviours are implemented using these basic
soccer skills. The literature study also revealed that strategies in the DMM
are usually developed using a hand-coded approach in the RoboCup SSL
domain, i.e., a specific and fixed strategy is coded, while in other leagues a
Machine Learning (ML) approach, Reinforcement Learning (RL) in particular,
is widely used. This led to the following research objective of this thesis,
namely to develop basic soccer skills using RL for the RoboCup Small Size
League. A second objective of this research is to develop a simulation environment
to facilitate the development of the DMM. A high-level simulator
was developed and validated as a result.
The temporal-difference value iteration algorithm with state-value functions
was used for RL, along with a Multi-Layer Perceptron (MLP) as a function
approximator. Two types of important soccer skills, namely shooting skills
and passing skills were developed using the RL and MLP combination. Nine
experiments were conducted to develop and evaluate these skills in various
playing situations. The results showed that the learning was very effective,
as the learning agent executed the shooting and passing tasks satisfactorily,
and further refinement is thus possible.
In conclusion, RL combined with MLP was successfully applied in this
research to develop two important basic soccer skills for robots in the
RoboCup SSL. These form a solid foundation for the development of a
complete DMM along with the simulation environment established in this
research. / AFRIKAANSE OPSOMMING: Hierdie studie het ontstaan as deel van 'n navorsingsprojek by Stellenbosch
Universiteit wat daarop gemik was om 'n span sokkerrobotte vir die
RoboCup Small Size League (SSL) te ontwikkel. Die besluitnemingsmodule
(BM) speel 'n belangrike rol in die RoboCup SSL, aangesien dit besluite vir
die robotte in die span maak. Hierdie navorsing fokus op ontwikkeling van
enkele komponente van die BM vir die span by SU.
'n Literatuurstudie het getoon dat die BM tipies ontwikkel word volgens
'n hiërargiese struktuur waarin basiese sokkervaardighede die fundamentele
boublokke vorm en hoëvlak spangedrag word dan gerealiseer deur hierdie
basiese vaardighede te gebruik. Die literatuur het ook getoon dat strategieë in die BM van die RoboCup SSL domein gewoonlik ontwikkel word deur
'n hand-gekodeerde benadering, dit wil s^e, 'n baie spesifieke en vaste strategie
word gekodeer, terwyl masjienleer (ML) en versterkingsleer (VL) wyd in
ander ligas gebruik word. Dit het gelei tot die navorsingsdoelwit in hierdie
tesis, naamlik om basiese sokkervaardighede vir robotte in die RoboCup SSL
te ontwikkel. 'n Tweede doelwit was om 'n simulasie-omgewing te ontwikkel
wat weer die ontwikkeling van die BM sou fasiliteer. Hierdie simulator is
suksesvol ontwikkel en gevalideer.
Die tydwaarde-verskil iterariewe algoritme met toestandwaarde-funksies is
gebruik vir VL saam met 'n multi-laag perseptron (MLP) vir funksiebenaderings.
Twee belangrike sokkervaardighede, naamlik doelskop- en aangeevaardighede
is met hierdie kombinasie van VL en MLP ontwikkel. Nege
eksperimente is uitgevoer om hierdie vaardighede in verskillende speelsituasies
te ontwikkel en te evalueer. Volgens die resultate was die leerproses baie
effektief, aangesien die leer-agent die doelskiet- en aangeetake bevredigend
uitgevoer het, en verdere verfyning is dus moontlik.
Die gevolgtrekking is dat VL gekombineer met MLP suksesvol toegepas is
in hierdie navorsingswerk om twee belangrike, basiese sokkervaardighede vir
robotte in die RoboCup SSL te ontwikkel. Dit vorm 'n sterk fondament vir
die ontwikkeling van 'n volledige BM tesame met die simulasie-omgewing
wat in hierdie werk daargestel is.
|
55 |
Využití umělých neuronových sítí pro předpověď ledových jevů na dolní Berounce / Using artifical neural network for ice phenomena prediction on the lower BerounkaŠebestová, Lucie January 2016 (has links)
Ice phenomena on watercourses are commonly occurring effect in winter period. In most places do not cause any complication, but in certain places their occurrence is more frequent and in conjunction with forming ice phenomena into dangerous, as a break-up ice jam or a freeze-up ice jam, can lead to the formation of ice flood. Such places is affected lower Berounka watercourse in section Křivoklát - Vltava confluence. Occurrence and formation of ice phenomena depends on ice regime, which lower Berounka causing frequent problems. Ice regime is the interplay of many factors and ice phenomena are thus generally very difficult to predict because of strongly nonlinear relationships. Artificial neural networks excel in ability to learn on examples, in this case historical data, and ability to apply the knowledge gained on the data present and the future. This work uses multilayer perceptron neural network to realization of ice phenomena prediction based on historical flow and temperature data from the years 1887 - 1940 from the measuring station Křivoklát, which is a place of frequent occurrence of dangerous ice phenomena. The results provided by the learned neural network are comparable to the standard model used in modeling of ice phenomena. Obtained outputs confirmed the possibility of the successful application of neural networks in this area. Their use is possible as e.g. a part of information (warning) system or a system for predicting the occurrence of ice phenomena during winter season, which may lead to the alleviation of their impact on watercourse, surrounding area and residents.
|
56 |
Deep Learning based Classification of FDG-PET Data for Alzheimer's DiseaseJanuary 2017 (has links)
abstract: Alzheimer’s Disease (AD), a neurodegenerative disease is a progressive disease that affects the brain gradually with time and worsens. Reliable and early diagnosis of AD and its prodromal stages (i.e. Mild Cognitive Impairment(MCI)) is essential. Fluorodeoxyglucose (FDG) positron emission tomography (PET) measures the decline in the regional cerebral metabolic rate for glucose, offering a reliable metabolic biomarker even on presymptomatic AD patients. PET scans provide functional information that is unique and unavailable using other types of imaging. The computational efficacy of FDG-PET data alone, for the classification of various Alzheimer’s Diagnostic categories (AD, MCI (LMCI, EMCI), Control) has not been studied. This serves as motivation to correctly classify the various diagnostic categories using FDG-PET data. Deep learning has recently been applied to the analysis of structural and functional brain imaging data. This thesis is an introduction to a deep learning based classification technique using neural networks with dimensionality reduction techniques to classify the different stages of AD based on FDG-PET image analysis.
This thesis develops a classification method to investigate the performance of FDG-PET as an effective biomarker for Alzheimer's clinical group classification. This involves dimensionality reduction using Probabilistic Principal Component Analysis on max-pooled data and mean-pooled data, followed by a Multilayer Feed Forward Neural Network which performs binary classification. Max pooled features result into better classification performance compared to results on mean pooled features. Additionally, experiments are done to investigate if the addition of important demographic features such as Functional Activities Questionnaire(FAQ), gene information helps improve performance. Classification results indicate that our designed classifiers achieve competitive results, and better with the additional of demographic features. / Dissertation/Thesis / Masters Thesis Computer Science 2017
|
57 |
[en] SUPERVISED LEARNING INCREMENTAL FEATURE INDUCTION AND SELECTION / [pt] INDUÇÃO E SELEÇÃO INCREMENTAIS DE ATRIBUTOS NO APRENDIZADO SUPERVISIONADOEDUARDO NEVES MOTTA 13 January 2017 (has links)
[pt] A indução de atributos não lineares a partir de atributos básicos é um modo de obter modelos preditivos mais precisos para problemas de classificação. Entretanto, a indução pode causar o rápido crescimento do número de atributos, resultando usualmente em overfitting e em modelos com baixo poder de generalização. Para evitar esta consequência indesejada, técnicas de regularização são aplicadas, para criar um compromisso entre um reduzido conjunto de atributos representativo do domínio e a capacidade de generalização
Neste trabalho, descrevemos uma abordagem de aprendizado de máquina supervisionado com indução e seleção incrementais de atributos. Esta abordagem integra árvores de decisão, support vector machines e seleção de atributos utilizando perceptrons esparsos em um framework de aprendizado que chamamos IFIS – Incremental Feature Induction and Selection. Usando o IFIS, somos capazes de criar modelos regularizados não lineares de alto desempenho utilizando um algoritmo com modelo linear. Avaliamos o nosso
sistema em duas tarefas de processamento de linguagem natural em dois idiomas. Na primeira tarefa, anotação morfossintática, usamos dois corpora, o corpus WSJ em língua inglesa e o Mac-Morpho em Português. Em ambos, alcançamos resultados competitivos com o estado da arte reportado na literatura, alcançando as acurácias de 97,14 por cento e 97,13 por cento, respectivamente. Na segunda tarefa, análise de dependência, utilizamos o corpus da CoNLL 2006 Shared Task em português, ultrapassando os resultados reportados durante aquela competição e alcançando resultados competitivos com o estado da arte para esta tarefa, com a métrica UAS igual a 92,01 por cento. Com a regularização usando um perceptron esparso, geramos modelos SVM que são até 10 vezes menores, preservando sua acurácia. A redução dos
modelos é obtida através da regularização dos domínios dos atributos, que atinge percentuais de até 99 por cento. Com a regularização dos modelos, alcançamos uma redução de até 82 por cento no tamanho físico dos modelos. O tempo de predição do modelo compacto é reduzido em até 84 por cento. A redução dos domínios e modelos permite também melhorar a engenharia de atributos, através da análise dos domínios compactos e da introdução incremental de novos atributos. / [en] Non linear feature induction from basic features is a method of generating predictive models with higher precision for classification problems. However, feature induction may rapidly lead to a huge number of features, causing overfitting and models with low predictive power. To prevent this side effect, regularization techniques are employed to obtain a trade-off between a reduced feature set representative of the domain and generalization power. In this work, we describe a supervised machine learning approach that incrementally inducts and selects feature conjunctions derived from base features. This approach integrates decision trees, support vector machines and feature selection using sparse perceptrons in a machine learning framework named IFIS – Incremental Feature Induction and Selection. Using IFIS, we generate regularized non-linear models with high performance using a linear algorithm. We evaluate our system in two natural language processing tasks in two different languages. For the first task, POS tagging, we use two corpora,
WSJ corpus for English, and Mac-Morpho for Portuguese. Our results are competitive with the state-of-the-art performance in both, achieving accuracies of 97.14 per cent and 97.13 per cent, respectively. In the second task, Dependency Parsing, we use the CoNLL 2006 Shared Task Portuguese corpus, achieving better results than those reported during that competition and competitive with the state-of-the-art for this task, with UAS score of 92.01 per cent. Applying model regularization using a sparse perceptron, we obtain SVM
models 10 times smaller, while maintaining their accuracies. We achieve model reduction by regularization of feature domains, which can reach 99 per cent. Using the regularized model we achieve model physical size shrinking of up to 82 per cent. The prediction time is cut by up to 84 per cent. Domains and models downsizing also allows enhancing feature engineering, through compact domain analysis and incremental inclusion of new features.
|
58 |
Možnosti využití neuronových sítí v síťových prvcích / Potential application of neural networks in network elementsBabnič, Patrik January 2011 (has links)
The goal was to get acquainted with the problems of network elements to describe neural networks that can be used to manage such a feature. The theoretical part deals with the neural networks from their inception to the present. It focuses mainly on the network, witch can be used for management control. These are the two network: Hopfield network and Kohonen network. The practical part deals with the network element model and ist implementation. It contains a practical element model using a neural network, witch is controlled by a network element.
|
59 |
Využití umělé inteligence v kryptografii / The use of artificial intelligence in cryptographyLavický, Vojtěch January 2012 (has links)
Goal of this thesis is to get familiar with problematics of neural networks and commonly used security protocols in cryptography. Theoretical part of the thesis is about neural networks theory and chooses best suitable type of neural network to use in cryptographic model. In practical part, a new type of security protocol is created, using chosen neural network.
|
60 |
Self-Organizing Error-Driven (Soed) Artificial Neural Network (Ann) for Smarter ClassificationJafari-Marandi, Ruholla 04 May 2018 (has links)
Classification tasks are an integral part of science, industry, medicine, and business; being such a pervasive technique, its smallest improvement is valuable. Artificial Neural Network (ANN) is one of the strongest techniques used in many disciplines for classification. The ANN technique suffers from drawbacks such as intransparency in spite of its high prediction power. In this dissertation, motivated by learning styles in human brains, ANN’s shortcomings are assuaged and its learning power is improved. Self-Organizing Map (SOM), an ANN variation which has strong unsupervised power, and Feedforward ANN, traditionally used for classification tasks, are hybridized to solidify their benefits and help remove their limitations. These benefits are in two directions: enhancing ANN’s learning power, and improving decision-making. First, the proposed method, named Self-Organizing Error-Driven (SOED) Artificial Neural Network (ANN), shows significant improvements in comparison with usual ANNs. We show SOED is a more accurate, more reliable, and more transparent technique through experimentation with five famous benchmark datasets. Second, the hybridization creates space for inclusion of decision-making goals at the level of ANN’s learning. This gives the classifier the opportunity to handle the inconclusiveness of the data smarter and in the direction of decision-making goals. Through three case studies, naming 1) churn decision analytics, 2) breast cancer diagnosis, and 3) quality control decision making through thermal monitoring of additive manufacturing processes, this novel and cost-sensitive aspect of SOED has been explored and lead to much quantified improvement in decision-making.
|
Page generated in 0.0586 seconds