Log in

Relevant bibliographies by topics / Artificial Neural Network Training / Dissertations / Theses

To see the other types of publications on this topic, follow the link: Artificial Neural Network Training.

Dissertations / Theses on the topic 'Artificial Neural Network Training'

Author: Grafiati

Published: 4 June 2021

Last updated: 18 February 2022

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 dissertations / theses for your research on the topic 'Artificial Neural Network Training.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.

1

Rimer, Michael Edwin. "Improving Neural Network Classification Training." Diss., CLICK HERE for online access, 2007. http://contentdm.lib.byu.edu/ETD/image/etd2094.pdf.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Åström, Fredrik. "Neural Network on Compute Shader : Running and Training a Neural Network using GPGPU." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-2036.

Full text

Abstract:

In this thesis I look into how one can train and run an artificial neural network using Compute Shader and what kind of performance can be expected. An artificial neural network is a computational model that is inspired by biological neural networks, e.g. a brain. Finding what kind of performance can be expected was done by creating an implementation that uses Compute Shader and then compare it to the FANN library, i.e. a fast artificial neural network library written in C. The conclusion is that you can improve performance by training an artificial neural network on the compute shader as long as you are using non-trivial datasets and neural network configurations.

APA, Harvard, Vancouver, ISO, and other styles

3

Sneath, Evan B. "Artificial neural network training for semi-autonomous robotic surgery applications." University of Cincinnati / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1416231638.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Inoue, Isao. "On the Effect of Training Data on Artificial Neural Network Models for Prediction." 名古屋大学大学院国際言語文化研究科, 2010. http://hdl.handle.net/2237/14090.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Kaster, Joshua M. "Training Convolutional Neural Network Classifiers Using Simultaneous Scaled Supercomputing." University of Dayton / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1588973772607826.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Buys, Stefan. "Genetic algorithm for Artificial Neural Network training for the purpose of Automated Part Recognition." Thesis, Nelson Mandela Metropolitan University, 2012. http://hdl.handle.net/10948/d1008356.

Full text

Abstract:

Object or part recognition is of major interest in industrial environments. Current methods implement expensive camera based solutions. There is a need for a cost effective alternative to be developed. One of the proposed methods is to overcome the hardware, camera, problem by implementing a software solution. Artificial Neural Networks (ANN) are to be used as the underlying intelligent software as they have high tolerance for noise and have the ability to generalize. A colleague has implemented a basic ANN based system comprising of an ANN and three cost effective laser distance sensors. However, the system is only able to identify 3 different parts and needed hard coding changes made by trial and error. This is not practical for industrial use in a production environment where there are a large quantity of different parts to be identified that change relatively regularly. The ability to easily train more parts is required. Difficulties associated with traditional mathematically guided training methods are discussed, which leads to the development of a Genetic Algorithm (GA) based evolutionary training method that overcomes these difficulties and makes accurate part recognition possible. An ANN hybridised with GA training is introduced and a general solution encoding scheme which is used to encode the required ANN connection weights. Experimental tests were performed in order to determine the ideal GA performance and control parameters as studies have indicated that different GA control parameters can lead to large differences in training accuracy. After performing these tests, the training accuracy was analyzed by investigation into GA performance as well as hardware based part recognition performance. This analysis identified the ideal GA control parameters when training an ANN for the purpose of part recognition and showed that the ANN generally trained well and could generalize well on data not presented to it during training.

APA, Harvard, Vancouver, ISO, and other styles

7

Griffin, Glenn R. "Predicting Naval Aviator Flight Training Performances using Multiple Regression and an Artificial Neural Network." NSUWorks, 1995. http://nsuworks.nova.edu/gscis_etd/548.

Full text

Abstract:

The Navy needs improved methods for assigning naval aviators (pilots) to fixed-wing and rotary-winged aircraft. At present, individual flight grades in primary training are used to assign naval aviator trainees to intermediate fixed wing or helicopter training. This study evaluated the potential of a series of single- and multitask tests to account for additional significant variance in the prediction of flight grade training performance for a sample of naval aviator trainees. Subjects were tested on a series of cognitive and perceptual psychomotor tests. The subjects then entered the Navy Flight Training Program. Subject's flight grades were obtained at the end of primary training. Multiple regression and artificial neural network procedures were evaluated to determine their relative efficiency in the prediction of flight grade training performance. All single- and multitask test measures evaluated as a part of this study were significantly related to the primary training flight grade criterion. Two psychomotor and one dichotic listening test measures contributed significant added variance to a multiple regression equation , beyond that of selection tests E (5, 428) = 27.19, R squared = .24, multiple R = .49 , 2 < .01. A follow-on analysis indicated a split-half validation correlation coefficient of £ = .38, 2 < .01 using multiple regression and as high as £ = .41, 2 < .01 using a neural network procedure. No statistically significant differences were found between the correlation coefficients resulting from the application of multiple regression and neural network validation procedures. Both procedures predicted the flight grade criterion equally well, although the neural network applications consistently provided slightly higher correlations between actual and predicted flight grades.

APA, Harvard, Vancouver, ISO, and other styles

8

Hsu, Kuo-Lin, Hoshin Vijai Gupta, and Soroosh Sorooshian. "A SUPERIOR TRAINING STRATEGY FOR THREE-LAYER FEEDFORWARD ARTIFICIAL NEURAL NETWORKS." Department of Hydrology and Water Resources, University of Arizona (Tucson, AZ), 1996. http://hdl.handle.net/10150/614171.

Full text

Abstract:

A new algorithm is proposed for the identification of three-layer feedforward artificial neural networks. The algorithm, entitled LLSSIM, partitions the weight space into two major groups: the input- hidden and hidden -output weights. The input- hidden weights are trained using a multi -start SIMPLEX algorithm and the hidden -output weights are identified using a conditional linear- least- square estimation approach. Architectural design is accomplished by progressive addition of nodes to the hidden layer. The LLSSIM approach provides globally superior weight estimates with fewer function evaluations than the conventional back propagation (BPA) and adaptive back propagation (ABPA) strategies. Monte -carlo testing on the XOR problem, two function approximation problems, and a rainfall- runoff modeling problem show LLSSIM to be more effective, efficient and stable than BPA and ABPA.

APA, Harvard, Vancouver, ISO, and other styles

9

George, Abhinav Kurian. "Fault tolerance and re-training analysis on neural networks." University of Cincinnati / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1552391639148868.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Chen, Lihui. "Modelling continuous sequential behaviour to enhance training and generalization in neural networks." Thesis, University of St Andrews, 1993. http://hdl.handle.net/10023/13485.

Full text

Abstract:

This thesis is a conceptual and empirical approach to embody modelling of continuous sequential behaviour in neural learning. The aim is to enhance the feasibility of training and capacity for generalisation. By examining the sequential aspects of the passing of time in a neural network, it is suggested that an alteration to the usual goal weight condition may be made to model these aspects. The notion of a goal weight path is introduced, with a path-based backpropagation (PBP) framework being proposed. Two models using PBP have been investigated in the thesis. One is called Feedforward Continuous BackPropagation (FCBP) which is a generalization of conventional BackPropagation; the other is called Recurrent Continuous BackPropagation (RCBP) which provides a neural dynamic system for I/O associations. Both models make use of the continuity underlying analogue-binary associations and analogue-analogue associations within a fixed neural network topology. A graphical simulator cbptool for Sun workstations has been designed and implemented for supporting the research. The capabilities of FCBP and RCBP have been explored through experiments. The results for FCBP and RCBP confirm the modelling theory. The fundamental alteration made on conventional backpropagation brings substantial improvement in training and generalization to enhance the power of backpropagation.

APA, Harvard, Vancouver, ISO, and other styles

11

Kirchner, William Thomas. "Ultrasonic acoustic health monitoring of ball bearings using neural network pattern classification of power spectral density." Thesis, Virginia Tech, 2009. http://hdl.handle.net/10919/36130.

Full text

Abstract:

This thesis presents a generic passive non-contact based acoustic health monitoring approach using ultrasonic acoustic emissions (UAE) to facilitate classification of bearing health via neural networks. This generic approach is applied to classifying the operating condition of conventional ball bearings. The acoustic emission signals used in this study are in the ultrasonic range (20-120 kHz), which is significantly higher than the majority of the research in this area thus far. A direct benefit of working in this frequency range is the inherent directionality of the microphones capable of measurement in this range, which becomes particularly useful when operating in environments with low signal-to-noise ratios. Using the UAE power spectrum signature, it is possible to pose the health monitoring problem as a multi-class classification problem, and make use of a multi-layer artificial neural network (ANN) to classify the UAE signature. One major problem limiting the usefulness of ANN's for failure classification is the need for large quantities of training data. Artificial training data, based on statistical properties of a significantly smaller experimental data set is created using the combination of a normal distribution and a coordinate transformation. The artificial training data provides a sufficient sized data set to train the neural network, as well as overcome the curse of dimensionality. The combination of the artificial training methods and ultrasonic frequency range being used results in an approach generic enough to suggest that this particular method is applicable to a variety of systems and components where persistent UAE exist.<br>Master of Science

APA, Harvard, Vancouver, ISO, and other styles

12

Sêcco, Ney Rafael. "Training artificial neural networks to predict aerodynamic coefficients of airliner wing-fuselage configurations." Instituto Tecnológico de Aeronáutica, 2014. http://www.bd.bibl.ita.br/tde_busca/arquivo.php?codArquivo=2955.

Full text

Abstract:

Multi-disciplinary Design Optimization highly demands computational resources, therefore it is important to develop design tools with low computational cost without compromising the fidelity of the model. The main goal of this work was to establish a methodology of training artificial neural networks for specific purposes of aircraft aerodynamic design, in order to substitute a computational fluid dynamics software in an optimization framework. This neural network would predict the lift and drag coefficients for an airliner';s wing-fuselage configuration based on its planform, airfoil, and flight condition parameters. This work also aimed to find the structure and the size of the network that best suits this problem, setting up references for future works. The aerodynamic database required for the neural network training was generated with a full-potential multiblock code. The training used the back propagation algorithm, the scaled conjugate gradient algorithm, and the Nguyen-Widrow weight initialization. Networks with different numbers of neurons were evaluated in order to minimize the regression error. The optimum networks reduced the computation time for the calculations of the aerodynamic coefficients in 4000 times when compared with the full-potential code. The average absolute errors obtained were of 0.004 and 0.0005 for lift and drag coefficients, respectively. We also propose an adapted version of the back propagation algorithm that allows the computation of gradients for optimization tasks using the artificial neural networks.

APA, Harvard, Vancouver, ISO, and other styles

13

Meehan, Patrick James. "Development of a Water Cloud Radiance Model for Use in Training an Artificial Neural Network to Recover Cloud Properties from Sun Photometer Observations." Thesis, Virginia Tech, 2021. http://hdl.handle.net/10919/103742.

Full text

Abstract:

As the planetary climate continues to evolve, it is important to build an accurate long-term climate record. State-of-the-art atmospheric science requires a variety of approaches to the measurement of the atmospheric structure and composition. This thesis supports the possibility of inferring cloud properties from sun photometer observations of the cloud solar aureole using an artificial neural network (ANN). Training of an ANN requires a large number of input and output parameter sets. A cloud radiance model is derived that takes into consideration the cloud depth, the mean size of the cloud water particles, and the cloud liquid water content. The cloud radiance model derived here is capable of considering the wavelength of the incident sunlight and the cloud lateral dimensions as parameters; however, here we consider only one wavelength—550 nm—and one lateral dimension—500 m—to demonstrate its performance. The cloud radiance model is then used to generate solar aureole profiles corresponding to the cloud parameters as they would be observed using a sun photometer. Coefficients representative of the solar aureole profiles may then be used as inputs to a trained ANN to infer the parameters used to generate the profile. This process is demonstrated through examples. A manuscript submitted for possible publication based on an early version of the cloud radiance model was deemed naïve by reviewers, ultimately leading to improvements documented here.<br>Master of Science<br>The Earth's climate is driven by heat from the sun and the exchange of heat between the Earth and space. The role of clouds is paramount in this process. One aspect of "cloud forcing" is cloud structure and composition. Required measures may be obtained by satellite or surface-based observations. Described here is the creation of a numerical model that calculates the disposition of individual bundles of light within water clouds. The clouds created in the model are all described by the mean size of the cloud water droplets, the amount of water in the cloud, and cloud depth. Changing these factors relative to each other changes the amount of light that traverses the cloud and the angle at which the individual bundles of light leave the cloud as measured using a device called a sun photometer. The measured amount and angle of bundles of light leaving the cloud are used to recover the parameters that characterize the cloud; i.e., the size of the cloud water droplets, the amount of water in the cloud, and the cloud depth. Two versions of the cloud radiance model are described.

APA, Harvard, Vancouver, ISO, and other styles

14

Geisen, Stefan [Verfasser], Ekkehard [Akademischer Betreuer] Sachs, and Volker [Akademischer Betreuer] Schulz. "Robust Training of Artificial Neural Networks via p-Quasinorms / Stefan Geisen ; Ekkehard Sachs, Volker Schulz." Trier : Universität Trier, 2020. http://d-nb.info/1215904975/34.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Knutsson, Magnus, and Linus Lindahl. "A COMPARATIVE STUDY OF FFN AND CNN WITHIN IMAGE RECOGNITION : The effects of training and accuracy of different artificial neural network designs." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17214.

Full text

Abstract:

Image recognition and -classification is becoming more important as the need to be able to process large amounts of images is becoming more common. The aim of this thesis is to compare two types of artificial neural networks, FeedForward Network and Convolutional Neural Network, to see how these compare when performing the task of image recognition. Six models of each type of neural network was created that differed in terms of width, depth and which activation function they used in order to learn. This enabled the experiment to also see if these parameters had any effect on the rate which a network learn and how the network design affected the validation accuracy of the models. The models were implemented using the API Keras, and trained and tested using the dataset CIFAR-10. The results showed that within the scope of this experiment the CNN models were always preferable as they achieved a statistically higher validation accuracy compared to their FFN counterparts.

APA, Harvard, Vancouver, ISO, and other styles

16

Zhao, Yi. "Combination of Wireless sensor network and artifical neuronal network : a new approach of modeling." Thesis, Toulon, 2013. http://www.theses.fr/2013TOUL0013/document.

Full text

Abstract:

Face à la limitation de la modélisation paramétrique, nous avons proposé dans cette thèse une procédure standard pour combiner les données reçues a partir de Réseaux de capteurs sans fils (WSN) pour modéliser a l'aide de Réseaux de Neurones Artificiels (ANN). Des expériences sur la modélisation thermique ont permis de démontrer que la combinaison de WSN et d'ANN est capable de produire des modèles thermiques précis. Une nouvelle méthode de formation "Multi-Pattern Cross Training" (MPCT) a également été introduite dans ce travail. Cette méthode permet de fusionner les informations provenant de différentes sources de données d'entraînements indépendants (patterns) en un seul modèle ANN. D'autres expériences ont montré que les modèles formés par la méthode MPCT fournissent une meilleure performance de généralisation et que les erreurs de prévision sont réduites. De plus, le modèle de réseau neuronal basé sur la méthode MPCT a montré des avantages importants dans le multi-variable Model Prédictive Control (MPC). Les simulations numériques indiquent que le MPC basé sur le MPCT a surpassé le MPC multi-modèles au niveau de l'efficacité du contrôle<br>A Wireless Sensor Network (WSN) consisting of autonomous sensor nodes can provide a rich stream of sensor data representing physical measurements. A well built Artificial Neural Network (ANN) model needs sufficient training data sources. Facing the limitation of traditional parametric modeling, this paper proposes a standard procedure of combining ANN and WSN sensor data in modeling. Experiments on indoor thermal modeling demonstrated that WSN together with ANN can lead to accurate fine grained indoor thermal models. A new training method "Multi-Pattern Cross Training" (MPCT) is also introduced in this work. This training method makes it possible to merge knowledge from different independent training data sources (patterns) into a single ANN model. Further experiments demonstrated that models trained by MPCT method shew better generalization performance and lower prediction errors in tests using different data sets. Also the MPCT based Neural Network Model has shown advantages in multi-variable Neural Network based Model Predictive Control (NNMPC). Software simulation and application results indicate that MPCT implemented NNMPC outperformed Multiple models based NNMPC in online control efficiency

APA, Harvard, Vancouver, ISO, and other styles

17

Melcherson, Tim. "Image Augmentation to Create Lower Quality Images for Training a YOLOv4 Object Detection Model." Thesis, Uppsala universitet, Signaler och system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-429146.

Full text

Abstract:

Research in the Arctic is of ever growing importance, and modern technology is used in news ways to map and understand this very complex region and how it is effected by climate change. Here, animals and vegetation are tightly coupled with their environment in a fragile ecosystem, and when the environment undergo rapid changes it risks damaging these ecosystems severely. Understanding what kind of data that has potential to be used in artificial intelligence, can be of importance as many research stations have data archives from decades of work in the Arctic. In this thesis, a YOLOv4 object detection model has been trained on two classes of images to investigate the performance impacts of disturbances in the training data set. An expanded data set was created by augmenting the initial data to contain various disturbances. A model was successfully trained on the augmented data set and a correlation between worse performance and presence of noise was detected, but changes in saturation and altered colour levels seemed to have less impact than expected. Reducing noise in gathered data is seemingly of greater importance than enhancing images with lacking colour levels. Further investigations with a larger and more thoroughly processed data set is required to gain a clearer picture of the impact of the various disturbances.

APA, Harvard, Vancouver, ISO, and other styles

18

Bhalala, Smita Ashesh 1966. "Modified Newton's method for supervised training of dynamical neural networks for applications in associative memory and nonlinear identification problems." Thesis, The University of Arizona, 1991. http://hdl.handle.net/10150/277969.

Full text

Abstract:

There have been several innovative approaches towards realizing an intelligent architecture that utilizes artificial neural networks for applications in information processing. The development of supervised training rules for updating the adjustable parameters of neural networks has received extensive attention in the recent past. In this study, specific learning algorithms utilizing modified Newton's method for the optimization of the adjustable parameters of a dynamical neural network are developed. Computer simulation results show that the convergence performance of the proposed learning schemes match very closely that of the LMS learning algorithm for applications in the design of associative memories and nonlinear mapping problems. However, the implementation of the modified Newton's method is complex due to the computation of the slope of the nonlinear sigmoidal function, whereas, the LMS algorithm approximates the slope to be zero.

APA, Harvard, Vancouver, ISO, and other styles

19

Gróf, Zoltán. "Realizace rozdělujících nadploch." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2012. http://www.nusl.cz/ntk/nusl-219781.

Full text

Abstract:

The main aim of this master's thesis is to describe the subject of the implementation of decision boundaries with the help of artificial neural networks. The objective is to present theoretical knowledge concerning this field and on practical examples prove these statements. The work contains basic theoretical description of the field of pattern recognition and the field of feature based representation of objects. A classificator working on the basis of Bayes decision is presented in this part, and other types of classificators are named as well. The work then deals with artificial neural networks in more detail; it contains a theoretical description of their function and their abilities in the creation of decision boundaries in the feature plane. Examples are shown from literature for the use of neural networks in corresponding problems. As part of this work, the program ANN-DeBC was created using Matlab, for the generation of practical results about the usage of feed-forward neural networks for the implementation of decision boundaries. The work contains a detailed description of this program, and the achieved results are presented and analyzed. It is shown as well, how artificial neural networks are creating decision boundaries in the form of geometrical shapes. The effects of the chosen topology of the neural network and the number of training samples on the success of the classification are observed, and the minimal values of these parameters are determined for the successful creation of decision boundaries at the individual examples. Furthermore, it's presented how the neural networks behave at the classification of realistically distributed training samples, and what methods can affect the shape of the created decision boundaries.

APA, Harvard, Vancouver, ISO, and other styles

20

Santos, Júnior Carlos Roberto dos [UNESP]. "Uma nova abordagem de treinamento on-line para rede neural ARTMAP Fuzzy." Universidade Estadual Paulista (UNESP), 2017. http://hdl.handle.net/11449/152033.

Full text

Abstract:

Submitted by CARLOS ROBERTO DOS SANTOS JÚNIOR null (carlos9_rsj@hotmail.com) on 2017-10-26T17:32:23Z No. of bitstreams: 1 Tese_CarlosRSantosJr_biblioteca_final.pdf: 3193090 bytes, checksum: ce950f71ef02dd650ba662b7b8eea784 (MD5)<br>Approved for entry into archive by Monique Sasaki (sayumi_sasaki@hotmail.com) on 2017-10-31T18:06:36Z (GMT) No. of bitstreams: 1 santosjunior_cr_dr_ilha.pdf: 3193090 bytes, checksum: ce950f71ef02dd650ba662b7b8eea784 (MD5)<br>Made available in DSpace on 2017-10-31T18:06:36Z (GMT). No. of bitstreams: 1 santosjunior_cr_dr_ilha.pdf: 3193090 bytes, checksum: ce950f71ef02dd650ba662b7b8eea784 (MD5) Previous issue date: 2017-09-04<br>A evolução dos recursos de internet levou ao crescente aumento do fluxo de dados, e por consequência, a necessidade de modelos de classificação ou previsão que suportem uma aprendizagem online. A Rede Neural ARTMAP Fuzzy tem sido utilizada nas mais diversas áreas do conhecimento, no entanto, ainda é pouco explorada em aplicações de tempo real que exigem uma aprendizagem contínua. Neste trabalho, é proposto uma Rede Neural ARTMAP Fuzzy com treinamento continuado, capaz de adquirir conhecimento ao longo da classificação ou previsão. Modificações na arquitetura e no algoritmo de aprendizagem possibilitam à rede neural ativar o treinamento sempre que necessário. Para validar o modelo proposto foram realizadas duas aplicações, uma para previsão e outra para classificação, utilizando bases de dados benchmarks e comparado com a ARTMAP Fuzzy original. Os resultados mostraram a capacidade do modelo proposto em adquirir conhecimento ao longo das amostras apresentadas de forma estável e eficiente. Assim, este estudo contribui para a evolução da rede neural ARTMAP Fuzzy e apresenta o treinamento continuado como uma alternativa eficaz para aplicações de tempo real.<br>The evolution of internet resources has led to an increase in the flow of data, and consequently, the need for classification or forecasting models that support an online learning. The ARTMAP Fuzzy Neural Network has been used in several areas of knowledge, however, it is still little explored in real-time applications that require continuous learning. In this work, an ARTMAP Fuzzy Neural Network with continuous training is proposed, able to acquire knowledge along the classification or prediction. Modifications in the architecture and learning algorithm enable the neural network to activate training whenever necessary. To validate the proposed model two experiments were performed, one for forecasting and another for classification, using benchmark databases and compared with the original ARTMAP Fuzzy Neural Network. The results showed the ability of the proposed model to acquire knowledge along the presented samples in a stable and efficient way. Thus, this study contributes to the evolution of the ARTMAP Fuzzy neural network and presents the continuous training as an effective alternative to real-time applications.

APA, Harvard, Vancouver, ISO, and other styles

21

Galassi, Andrea. "Symbolic versus sub-symbolic approaches: a case study on training Deep Networks to play Nine Men’s Morris game." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/12859/.

Full text

Abstract:

Le reti neurali artificiali, grazie alle nuove tecniche di Deep Learning, hanno completamente rivoluzionato il panorama tecnologico degli ultimi anni, dimostrandosi efficaci in svariati compiti di Intelligenza Artificiale e ambiti affini. Sarebbe quindi interessante analizzare in che modo e in quale misura le deep network possano sostituire le IA simboliche. Dopo gli impressionanti risultati ottenuti nel gioco del Go, come caso di studio è stato scelto il gioco del Mulino, un gioco da tavolo largamente diffuso e ampiamente studiato. È stato quindi creato il sistema completamente sub-simbolico Neural Nine Men’s Morris, che sfrutta tre reti neurali per scegliere la mossa migliore. Le reti sono state addestrate su un dataset di più di 1.500.000 coppie (stato del gioco, mossa migliore), creato in base alle scelte di una IA simbolica. Il sistema ha dimostrato di aver imparato le regole del gioco proponendo una mossa valida in più del 99% dei casi di test. Inoltre ha raggiunto un’accuratezza del 39% rispetto al dataset e ha sviluppato una propria strategia di gioco diversa da quella della IA addestratrice, dimostrandosi un giocatore peggiore o migliore a seconda dell’avversario. I risultati ottenuti in questo caso di studio mostrano che, in questo contesto, la chiave del successo nella progettazione di sistemi AI allo stato dell’arte sembra essere un buon bilanciamento tra tecniche simboliche e sub-simboliche, dando più rilevanza a queste ultime, con lo scopo di raggiungere la perfetta integrazione di queste tecnologie.

APA, Harvard, Vancouver, ISO, and other styles

22

Gosal, Gurpreet Singh. "The use of Inverse Neural Networks in the Fast Design of Printed Lens Antennas." Thesis, Université d'Ottawa / University of Ottawa, 2015. http://hdl.handle.net/10393/32249.

Full text

Abstract:

In this thesis the major objective is the implementation of the inverse neural network concept in the design of printed lens (transmitarray) antenna. As it is computationally extensive to perform full-wave simulations for entire transmitarray structure and thereafter perform optimization, the idea is to generate a design database assuming that a unit cell of the transmitarray is situated inside a 2D infinite periodic structure. This way we generate a design database of transmission coefficient by varying the unit cell parameters. Since, for the actual design, we need dimensions for each cell on the transmitarray aperture and to do this we need to invert the design database. The major contribution of this thesis is the proposal and the implementation of database inversion methodology namely inverse neural network modelling. We provide the algorithms for carrying out the inversion process as well as provide check results to demonstrate the reliability of the proposed methodology. Finally, we apply this approach to design a transmitarray antenna, and measure its performance.

APA, Harvard, Vancouver, ISO, and other styles

23

Olsson, Tim, and Konrad Magnusson. "Training Artificial Neural Networks with Genetic Algorithms for Stock Forecasting : A comparative study between genetic algorithms and the backpropagation of errors algorithms for predicting stock prices." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-186447.

Full text

Abstract:

Accurate prediction of future stock market prices is of great importance to traders. The process can be automated using articial neural networks. However, the conventional backward propagation of errors algorithm commonly used for training the networks suffers from the local minima problem. This study investigates whether investing more computational resources into training an ar-ticial neural network using genetic algorithms over the conventional algorithm,to avoid the local minima problem, can result in higher prediction accuracy. The results indicate that there is no signicant increase in accuracy to gain by investing resources into training with genetic algorithms, using our proposed model.

APA, Harvard, Vancouver, ISO, and other styles

24

Horečný, Peter. "Metody segmentace obrazu s malými trénovacími množinami." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2020. http://www.nusl.cz/ntk/nusl-412996.

Full text

Abstract:

The goal of this thesis was to propose an image segmentation method, which is capable of effective segmentation process with small datasets. Recently published ODE neural network was used for this method, because its features should provide better generalization in case of tasks with only small datasets available. The proposed ODE-UNet network was created by combining UNet architecture with ODE neural network, while using benefits of both networks. ODE-UNet reached following results on ISBI dataset: Rand: 0,950272 and Info: 0,978061. These results are better than the ones received from UNet model, which was also tested in this thesis, but it has been proven that state of the art can not be outperformed using ODE neural networks. However, the advantages of ODE neural network over tested UNet architecture and other methods were confirmed, and there is still a room for improvement by extending this method.

APA, Harvard, Vancouver, ISO, and other styles

25

Pech, Thomas Joel. "A Deep-Learning Approach to Evaluating the Navigability of Off-Road Terrain from 3-D Imaging." Case Western Reserve University School of Graduate Studies / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=case1496377449249936.

Full text

APA, Harvard, Vancouver, ISO, and other styles

26

Dilan, Askin Rasim. "Unstructured Road Recognition And Following For Mobile Robots Via Image Processing Using Anns." Master's thesis, METU, 2010. http://etd.lib.metu.edu.tr/upload/12612047/index.pdf.

Full text

Abstract:

For an autonomous outdoor mobile robot ability to detect roads existing around is a vital capability. Unstructured roads are among the toughest challenges for a mobile robot both in terms of detection and navigation. Even though mobile robots use various sensors to interact with their environment, being a comparatively low-cost and rich source of information, potential of cameras should be fully utilized. This research aims to systematically investigate the potential use of streaming camera images in detecting unstructured roads. The investigation focused on the use of methods employing Artificial Neural Networks (ANNs). An exhaustive test process is followed where different kernel sizes and feature vectors are varied systematically where trainings are carried out via backpropagation in a feed-forward ANN. The thesis also claims a contribution in the creation of test data where truth images are created almost in realtime by making use of the dexterity of human hands. Various road profiles v ranging from human-made unstructured roads to trails are investigated. Output of ANNs indicating road regions is justified against the vanishing point computed in the scene and a heading vector is computed that is to keep the robot on the road. As a result, it is shown that, even though a robot cannot fully rely on camera images for heading computation as proposed, use of image based heading computation can provide a useful assistance to other sensors present on a mobile robot.

APA, Harvard, Vancouver, ISO, and other styles

27

BRUCE, WILLIAM, and OTTER EDVIN VON. "Artificial Neural Network Autonomous Vehicle : Artificial Neural Network controlled vehicle." Thesis, KTH, Maskinkonstruktion (Inst.), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-191192.

Full text

Abstract:

This thesis aims to explain how a Artificial Neural Network algorithm could be used as means of control for a Autonomous Vehicle. It describes the theory behind the neural network and Autonomous Vehicles, and how a prototype with a camera as its only input can be designed to test and evaluate the algorithms capabilites, and also drive using it. The thesis will show that the Artificial Neural Network can, with a image resolution of 100 × 100 and a training set with 900 images, makes decisions with a 0.78 confidence level.<br>Denna rapport har som mal att beskriva hur en Artificiellt Neuronnatverk al- goritm kan anvandas for att kontrollera en bil. Det beskriver teorin bakom neu- ronnatverk och autonoma farkoster samt hur en prototyp, som endast anvander en kamera som indata, kan designas for att testa och utvardera algoritmens formagor. Rapporten kommer visa att ett neuronnatverk kan, med bildupplos- ningen 100 × 100 och traningsdata innehallande 900 bilder, ta beslut med en 0.78 sakerhet.

APA, Harvard, Vancouver, ISO, and other styles

28

Manesco, Luis Fernando. "Modelagem de um processo fermentativo por rede Perceptron multicamadas com atraso de tempo." Universidade de São Paulo, 1996. http://www.teses.usp.br/teses/disponiveis/18/18133/tde-22012018-103016/.

Full text

Abstract:

A utilização de Redes Neurais Artificias para fins de identificação e controle de sistemas dinâmicos têm recebido atenção especial de muitos pesquisadores, principalmente no que se refere a sistemas não lineares. Neste trabalho é apresentado um estudo sobre a utilização de um tipo em particular de Rede Neural Artificial, uma Perceptron Multicamadas com Atraso de Tempo, na estimação de estados da etapa fermentativa do processo de Reichstein para produção de vitamina C. A aplicação de Redes Neurais Artificiais a este processo pode ser justificada pela existência de problemas associados à esta etapa, como variáveis de estado não mensuráveis e com incertezas de medida e não linearidade do processo fermentativo, além da dificuldade em se obter um modelo convencional que contemple todas as fases do processo. É estudado também a eficácia do algoritmo de Levenberg-Marquadt, na aceleração do treinamento da Rede Neural Artificial, além de uma comparação do desempenho de estimação de estados das Redes Neurais Artificiais estudadas com o filtro estendido de Kalman, baseado em um modelo não estruturado do processo fermentativo. A análise do desempenho das Redes Neurais Artificiais estudadas é avaliada em termos de uma figura de mérito baseada no erro médio quadrático sendo feitas considerações quanto ao tipo da função de ativação e o número de unidades da camada oculta. Os dados utilizados para treinamento e avaliação da Redes Neurais Artificiais foram obtidos de um conjunto de ensaios interpolados para o intervalo de amostragem desejado.<br>ldentification and Control of dynamic systems using Artificial Neural Networks has been widely investigated by many researchers in the last few years, with special attention to the application of these in nonlinear systems. ls this works, a study on the utilization of a particular type of Artificial Neural Networks, a Time Delay Multi Layer Perceptron, in the state estimation of the fermentative phase of the Reichstein process of the C vitamin production. The use of Artificial Neural Networks can be justified by the presence of problems, such as uncertain and unmeasurable state variables and process non-linearity, and by the fact that a conventional model that works on all phases of the fermentative processes is very difficult to obtain. The efficiency of the Levenberg Marquadt algorithm on the acceleration of the training process is also studied. Also, a comparison is performed between the studied Artificial Neural Networks and an extended Kalman filter based on a non-structured model for this fermentative process. The analysis of lhe Artificial Neural Networks is carried out using lhe mean square errors taking into consideration lhe activation function and the number of units presents in the hidden layer. A set of batch experimental runs, interpolated to the desired time interval, is used for training and validating the Artificial Neural Networks.

APA, Harvard, Vancouver, ISO, and other styles

29

Leija, Carlos Ivan. "An artificial neural network with reconfigurable interconnection network." To access this resource online via ProQuest Dissertations and Theses @ UTEP, 2008. http://0-proquest.umi.com.lib.utep.edu/login?COPT=REJTPTU0YmImSU5UPTAmVkVSPTI=&clientId=2515.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Alkharobi, Talal M. "Secret sharing using artificial neural network." Diss., Texas A&M University, 2004. http://hdl.handle.net/1969.1/1223.

Full text

Abstract:

Secret sharing is a fundamental notion for secure cryptographic design. In a secret sharing scheme, a set of participants shares a secret among them such that only pre-specified subsets of these shares can get together to recover the secret. This dissertation introduces a neural network approach to solve the problem of secret sharing for any given access structure. Other approaches have been used to solve this problem. However, the yet known approaches result in exponential increase in the amount of data that every participant need to keep. This amount is measured by the secret sharing scheme information rate. This work is intended to solve the problem with better information rate.

APA, Harvard, Vancouver, ISO, and other styles

31

Zhao, Lichen. "Random pulse artificial neural network architecture." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape17/PQDD_0006/MQ36758.pdf.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

Ng, Justin. "Artificial Neural Network-Based Robotic Control." DigitalCommons@CalPoly, 2018. https://digitalcommons.calpoly.edu/theses/1846.

Full text

Abstract:

Artificial neural networks (ANNs) are highly-capable alternatives to traditional problem solving schemes due to their ability to solve non-linear systems with a nonalgorithmic approach. The applications of ANNs range from process control to pattern recognition and, with increasing importance, robotics. This paper demonstrates continuous control of a robot using the deep deterministic policy gradients (DDPG) algorithm, an actor-critic reinforcement learning strategy, originally conceived by Google DeepMind. After training, the robot performs controlled locomotion within an enclosed area. The paper also details the robot design process and explores the challenges of implementation in a real-time system.

APA, Harvard, Vancouver, ISO, and other styles

33

Khazanova, Yekaterina. "Experiments with Neural Network Libraries." University of Cincinnati / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1527607591612278.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Brunger, Clifford A. "Artificial neural network modeling of damaged aircraft." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 1994. http://handle.dtic.mil/100.2/ADA283227.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Tang, Chuan Zhang. "Artificial neural network models for digital implementation." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1996. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/nq30298.pdf.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

Tupas, Ronald-Ray Tiñana. "Artificial neural network modelling of filtration performance." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape4/PQDD_0011/MQ59890.pdf.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Luan, Wenpeng. "Voltage ranking using artificial neural network method." Thesis, University of Strathclyde, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.366960.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Bataineh, Mohammad Hindi. "Artificial neural network for studying human performance." Thesis, University of Iowa, 2012. https://ir.uiowa.edu/etd/3259.

Full text

Abstract:

The vast majority of products and processes in industry and academia require human interaction. Thus, digital human models (DHMs) are becoming critical for improved designs, injury prevention, and a better understanding of human behavior. Although many capabilities in the DHM field continue to mature, there are still many opportunities for improvement, especially with respect to posture- and motion-prediction. Thus, this thesis investigates the use of artificial neural network (ANN) for improving predictive capabilities and for better understanding how and why human behave the way they do. With respect to motion prediction, one of the most challenging opportunities for improvement concerns computation speed. Especially, when considering dynamic motion prediction, the underlying optimization problems can be large and computationally complex. Even though the current optimization-based tools for predicting human posture are relatively fast and accurate and thus do not require as much improvement, posture prediction in general is a more tractable problem than motion prediction and can provide a test bead that can shed light on potential issues with motion prediction. Thus, we investigate the use of ANN with posture prediction in order to discover potential issues. In addition, directly using ANN with posture prediction provides a preliminary step towards using ANN to predict the most appropriate combination of performance measures (PMs) - what drives human behavior. The PMs, which are the cost functions that are minimized in the posture prediction problem, are typically selected manually depending on the task. This is perhaps the most significant impediment when using posture prediction. How does the user know which PMs should be used? Neural networks provide tools for solving this problem. This thesis hypothesizes that the ANN can be trained to predict human motion quickly and accurately, to predict human posture (while considering external forces), and to determine the most appropriate combination of PM(s) for posture prediction. Such capabilities will in turn provide a new tool for studying human behavior. Based on initial experimentation, the general regression neural network (GRNN) was found to be the most effective type of ANN for DHM applications. A semi-automated methodology was developed to ease network construction, training and testing processes, and network parameters. This in turn facilitates use with DHM applications. With regards to motion prediction, use of ANN was successful. The results showed that the calculation time was reduced from 1 to 40 minutes, to a fraction of a second without reducing accuracy. With regards to posture prediction, ANN was again found to be effective. However, potential issues with certain motion-prediction tasks were discovered and shed light on necessary future development with ANNs. Finally, a decision engine was developed using GRNN for automatically selecting four human PMs, and was shown to be very effective. In order to train this new approach, a novel optimization formulation was used to extract PM weights from pre-existing motion-capture data. Eventually, this work will lead to automatically and realistically driving predictive DHMs in a general virtual environment.

APA, Harvard, Vancouver, ISO, and other styles

39

Choi, Hyunjong. "Medical Image Registration Using Artificial Neural Network." DigitalCommons@CalPoly, 2015. https://digitalcommons.calpoly.edu/theses/1523.

Full text

Abstract:

Image registration is the transformation of different sets of images into one coordinate system in order to align and overlay multiple images. Image registration is used in many fields such as medical imaging, remote sensing, and computer vision. It is very important in medical research, where multiple images are acquired from different sensors at various points in time. This allows doctors to monitor the effects of treatments on patients in a certain region of interest over time. In this thesis, artificial neural networks with curvelet keypoints are used to estimate the parameters of registration. Simulations show that the curvelet keypoints provide more accurate results than using the Discrete Cosine Transform (DCT) coefficients and Scale Invariant Feature Transform (SIFT) keypoints on rotation and scale parameter estimation.

APA, Harvard, Vancouver, ISO, and other styles

40

Chambers, Mark Andrew. "Queuing network construction using artificial neural networks /." The Ohio State University, 2000. http://rave.ohiolink.edu/etdc/view?acc_num=osu1488193665234291.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Tsui, Kwok Ching. "Neural network design using evolutionary computing." Thesis, King's College London (University of London), 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.299918.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Baker, Thomas Edward. "Implementation limits for artificial neural networks." Full text open access at:, 1990. http://content.ohsu.edu/u?/etd,268.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Leong, Cheok Fan. "Approximation theory of multilayer feedforward artificial neural network." Thesis, University of Macau, 2002. http://umaclib3.umac.mo/record=b1446728.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Beckenkamp, Fábio Ghignatti. "A component architecture for artificial neural network systems." [S.l. : s.n.], 2002. http://deposit.ddb.de/cgi-bin/dokserv?idn=964923580.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Theramongkol, Phunsak. "Intelligent ozone-level forecasting using artificial neural network." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape4/PQDD_0021/MQ54752.pdf.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Zahra, Fathima. "Artificial neural network approach to transmission line relaying." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape11/PQDD_0001/MQ42465.pdf.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Horng, Der Fuh, and 洪得富. "The Comparison of Artificial-Neural-Network Training Structures." Thesis, 1993. http://ndltd.ncl.edu.tw/handle/59186168623107571339.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Shen, Tzung-Tza, and 沈宗澤. "Training Artificial Neural Network Using Genetic Algorithm and Conjugate Gradient Method." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/18262883491045855458.

Full text

Abstract:

碩士<br>國立成功大學<br>航空太空工程學系<br>89<br>The purpose of this study is to combine the conjugate gradient method(CG) and the genetic algorithm(GA) for the training of artificial neural networks(ANN). The back-propagation artificial neural network is a broadly used artificial neural network in many areas. It usually adopts the steepest descent method(SD) to search for a set of connection weights that minimizes the training error. But the convergence of the steepest descent method is very slow and easy to trap into a local optimal. In order to speed up the convergence, the conjugate gradient method searches the optimal weights along a set of conjugate directions in stead of steepest descent ones. But it still has the drawback of trapping into local optimals. The genetic algorithm is a global optimization method based on the Darwin’s principle of ‘’Survival of the fittest’’. The genetic algorithm always searches for the global optimal. In this study, we develop a hybrid method which combines the conjugate gradient method and the genetic algorithm to improve the convergence and successful rate for the training of artificial neural networks.

APA, Harvard, Vancouver, ISO, and other styles

49

Hsu, Chia-yung, and 徐家鏞. "Artificial Neural Network Incorporating Regional Information Training for Robust Speech Recognition." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/gptd26.

Full text

Abstract:

碩士<br>國立中央大學<br>資訊工程學系<br>103<br>Speech sounds is an essential element in human society. With the advance of science and technology, the proportion of people rely on computers to handle everything in our daily life more and more. In order to make the computer capable of handling speech data, speech recognition has become an important issue. Automatic speech recognition (ASR) in clean speech data can achieve good results but the environment we live is full of noise. As the speech SNR get lower and lower, the speech recognition accuracy inevitably decreased. For this reason, find a way to improve the noise speech recognize capability is important in our actual life. Recently, ASR using neural network (NN) based acoustic model (AM) has achieved significant improvements. However, the mismatch (including speaker and speaking environment) of training and testing conditions still confines the applicability of ASR. This paper proposes a novel approach that combines the environment clustering (EC) and mixture of experts (MOE) algorithms (thus the proposed approach is termed EC-MOE) to enhance the robustness of ASR against mismatches. In the offline phase, we split the entire training set into several subsets, with each subset characterizing a specific speaker and speaking environment. Then, we use each subset of training data to prepare an NN-based AM. In the online phase, we use a Gaussian mixture model (GMM)-gate to determine the optimal output from the multiple NN-based AMs to render the final recognition results. We evaluated the proposed EC-MOE approach on the Aurora 2 continuous digital speech recognition task. Comparing to the baseline system, where only a single NN-based AM is used for recognition, the proposed approach achieves a clear word error rate (WER) reduction of 6.86 % (5.25% to 4.89%).

APA, Harvard, Vancouver, ISO, and other styles

50

Tang, Jia-Ci, and 唐家麒. "Research on Artificial Neural Network Training Using Modified Particle Swarm Optimization." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/xe6ame.

Full text

Abstract:

碩士<br>義守大學<br>電機工程學系<br>105<br>In this research, the modified particle swarm optimization algorithm will be applied to the training of artificial neural networks for machine learning problems. This modified algorithm appropriately combines the standard particle swarm optimization and Lévy flight (very often used in cuckoo search algorithm) in order to escape from the local minima of the cost surface and to avoid the premature convergence of the candidate solutions. Three numerical examples will be used to illustrate the use of our proposed algorithm. Some comparisons of the performances using proposed algorithm and the standard particle swarm optimization will be made. Our programs were written in Python language.

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!