Log in

Relevant bibliographies by topics / Wide neural network / Dissertations / Theses

To see the other types of publications on this topic, follow the link: Wide neural network.

Dissertations / Theses on the topic 'Wide neural network'

Author: Grafiati

Published: 2 June 2025

Last updated: 31 July 2025

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 'Wide neural network.'

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

Brande, Julia K. Jr. "Computer Network Routing with a Fuzzy Neural Network." Diss., Virginia Tech, 1997. http://hdl.handle.net/10919/29685.

Full text

Abstract:

The growing usage of computer networks is requiring improvements in network technologies and management techniques so users will receive high quality service. As more individuals transmit data through a computer network, the quality of service received by the users begins to degrade. A major aspect of computer networks that is vital to quality of service is data routing. A more effective method for routing data through a computer network can assist with the new problems being encountered with today's growing networks. Effective routing algorithms use various techniques to determine the most

APA, Harvard, Vancouver, ISO, and other styles

2

Yu, Xiafei. "Wide Activated Separate 3D Convolution for Video Super-Resolution." Thesis, Université d'Ottawa / University of Ottawa, 2019. http://hdl.handle.net/10393/39974.

Full text

Abstract:

Video super-resolution (VSR) aims to recover a realistic high-resolution (HR) frame from its corresponding center low-resolution (LR) frame and several neighbouring supporting frames. The neighbouring supporting LR frames can provide extra information to help recover the HR frame. However, these frames are not aligned with the center frame due to the motion of objects. Recently, many video super-resolution methods based on deep learning have been proposed with the rapid development of neural networks. Most of these methods utilize motion estimation and compensation models as preprocessing to

APA, Harvard, Vancouver, ISO, and other styles

3

Viens, Francois (Joseph Lucien Francois) Carleton University Dissertation Engineering Electrical. "A neural network approach to detect traffic anomalies in a communication network." Ottawa, 1992.

Find full text

APA, Harvard, Vancouver, ISO, and other styles

4

Annergren, Björn. "Log Classification using a Shallow-and-Wide Convolutional Neural Network and Log Keys." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-239561.

Full text

Abstract:

A dataset consisting of logs describing results of tests from a single Build and Test process, used in a Continous Integration setting, is utilized to automate categorization of the logs according to failure types. Two different features are evaluated, words and log keys, using unordered document matrices as document representations to determine the viability of log keys. The experiment uses Multinomial Naive Bayes, MNB, classifiers and multi-class Support Vector Machines, SVM, to establish the performance of the different features. The experiment indicates that log keys are equivalent to usin

APA, Harvard, Vancouver, ISO, and other styles

5

Reginbald, Ivarsson Jón. "Scalable System-Wide Traffic Flow Predictions Using Graph Partitioning and Recurrent Neural Networks." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254896.

Full text

Abstract:

Traffic flow predictions are an important part of an Intelligent Transportation System as the ability to forecast accurately the traffic conditions in a transportation system allows for proactive rather than reactive traffic control. Providing accurate real-time traffic predictions is a challenging problem because of the nonlinear and stochastic features of traffic flow. An increasingly widespread deployment of traffic sensors in a growing transportation system produces greater volume of traffic flow data. This results in problems concerning fast, reliable and scalable traffic predictions.The

APA, Harvard, Vancouver, ISO, and other styles

6

Pakdel, Zahra. "Intelligent Instability Detection for Islanding Prediction." Diss., Virginia Tech, 2011. http://hdl.handle.net/10919/27715.

Full text

Abstract:

The goal of the proposed procedure in this dissertation is the implementation of phasor measurement unit (PMU) based instability detection for islanding prediction procedures using decision tree and neural network modeling. The islanding in the power system define as a separation of the coherent group of generators from the rest of the system due to contingencies, in the case that all generators are coherent together after introducing a fault, it is called stable or non-islanding. The main philosophy of islanding detection in the proposed methodology is to use decision trees and neural network

APA, Harvard, Vancouver, ISO, and other styles

7

Di, Luca Federico. "Rivelazione del Respiro Umano da Segnali UWB con Machine Learning e Deep Neural Network." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019.

Find full text

Abstract:

L'obbiettivo di questo elaborato è valutare le prestazioni di vari algoritmi di Machine Learning e Deep Learning nel distinguere tra le condizioni Non-Line-of-Sight (NLoS) e Line-of-Sight (LoS) e nel rivelare la presenza del respiro umano in condizioni NLoS, utilizzando segnali Ultra-Wide Band (UWB). A tal fine sono stati presi in considerazione quattro esperimenti: uno per la classificazione LoS-NLoS e tre per valutare l'efficacia degli stessi algoritmi nel distinguere tra le situazioni di presenza e assenza del respiro. I dati ottenuti tramite le varie campagne di misure sono stati elabora

APA, Harvard, Vancouver, ISO, and other styles

8

Dall'Olio, Daniele. "Applicazione di un algoritmo d’apprendimento basato su sistemi fuori dall’equilibrio a dati di Genome Wide Association." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/18499/.

Full text

Abstract:

Il fenomeno dell’apprendimento può essere studiato attraverso metodiche di Meccanica Statistica. A partire dalle Neural Networks è possibile descrivere il problema dell'apprendimento mediante un sistema di spin interagenti. Usando una descrizione all’equilibrio del sistema e sotto opportune condizioni, tale problema si dimostra computazionalmente complesso. Tuttavia, esistono algoritmi euristici in grado di risolvere lo stesso problema efficacemente. Si dimostra che questa apparente inconsistenza è dovuta al fatto che lo spazio delle soluzioni degli algoritmi euristici non coincida con quello

APA, Harvard, Vancouver, ISO, and other styles

9

Li, Vladimir. "Evaluation of the CNN Based Architectures on the Problem of Wide Baseline Stereo Matching." Thesis, KTH, Datorseende och robotik, CVAP, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-192476.

Full text

Abstract:

Three-dimensional information is often used in robotics and 3D-mapping. There exist several ways to obtain a three-dimensional map. However, the time of flight used in the laser scanners or the structured light utilized by Kinect-like sensors sometimes are not sufficient. In this thesis, we investigate two CNN based stereo matching methods for obtaining 3D-information from a grayscaled pair of rectified images.While the state-of-the-art stereo matching method utilize a Siamese architecture, in this project a two-channel and a two stream network are trained in an attempt to outperform the state

APA, Harvard, Vancouver, ISO, and other styles

10

Lundberg, Gustav. "Automatic map generation from nation-wide data sources using deep learning." Thesis, Linköpings universitet, Statistik och maskininlärning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-170759.

Full text

Abstract:

The last decade has seen great advances within the field of artificial intelligence. One of the most noteworthy areas is that of deep learning, which is nowadays used in everything from self driving cars to automated cancer screening. During the same time, the amount of spatial data encompassing not only two but three dimensions has also grown and whole cities and countries are being scanned. Combining these two technological advances enables the creation of detailed maps with a multitude of applications, civilian as well as military.This thesis aims at combining two data sources covering most

APA, Harvard, Vancouver, ISO, and other styles

11

Hajjar, Karl. "A dynamical analysis of infinitely wide neural networks." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASM001.

Full text

Abstract:

Durant la dernière décennie, les réseaux de neurones ont eu un succès retentissant dans de nombreuses tâches en pratique, cependant les arguments théoriques derrière ce succès restent insuffisants et une théorie mathématique appropriée pour étudier rigoureusement ces objets fait toujours défaut. Les limites des réseaux de neurones à largeur infinie sont récemment apparues comme une façon d'éclaircir certains aspects du problème. Dans cette thèse, nous étudions la limite des réseaux de neurones de largeur infinie avec une renormalisation particulière souvent dénommée ''champ moyen'' dans la lit

APA, Harvard, Vancouver, ISO, and other styles

12

Glória, Leonardo Siqueira. "Assessment of genome-wide prediction by using Bayesian regularized neural networks." Universidade Federal de Viçosa, 2015. http://www.locus.ufv.br/handle/123456789/6866.

Full text

Abstract:

Submitted by Amauri Alves (amauri.alves@ufv.br) on 2015-12-02T16:52:21Z No. of bitstreams: 1 texto completo.pdf: 4119749 bytes, checksum: abab366057d5b5d02a6202d32f277b7c (MD5)<br>Made available in DSpace on 2015-12-02T16:52:21Z (GMT). No. of bitstreams: 1 texto completo.pdf: 4119749 bytes, checksum: abab366057d5b5d02a6202d32f277b7c (MD5) Previous issue date: 2015-05-25<br>Coordenação de Aperfeiçoamento de Pessoal de Nível Superior<br>Recentemente, há um aumento de interesse na utilização de métodos não paramétricos, tais como redes neurais artificiais (RNA), na área de seleção genômica

APA, Harvard, Vancouver, ISO, and other styles

13

Paillassa, Maxime. "Détection robuste de sources astronomiques par réseaux de neurones à convolutions." Thesis, Bordeaux, 2020. http://www.theses.fr/2020BORD0147.

Full text

Abstract:

L'extraction de catalogues de sources fiables à partir des images est cruciale pour un large éventail de recherches en astronomie.Cependant, l'efficacité des méthodes de détection de source actuelles est sérieusement limitée dans les champs encombrés, ou lorsque les images sont contaminées par des défauts optiques, électroniques et environnementaux.Les performances en termes de fiabilité et de complétude sont aujourd'hui souvent insuffisantes au regard des exigences scientifiques des grands relevés d'imagerie.Dans cette thèse, nous développons de nouvelles méthodes pour produire des catalogues

APA, Harvard, Vancouver, ISO, and other styles

14

Chorier, Cécile. "La classification de cibles aquatiques par sonar large bande." Grenoble INPG, 1996. http://www.theses.fr/1996INPG0069.

Full text

Abstract:

En reconnaissance des especes de poissons par sonar large bande, l'etude est consacree aux poissons isoles, nageant librement en cuve. La classification se decompose en trois etapes: l'acquisition de donnees, l'extraction de parametres pertinents puis la decision. C'est pourquoi, le travail a d'abord consiste a mettre en uvre un systeme sonar adapte: large bande (20-140 khz). Pour maintenir le poisson dans le faisceau acoustique, une cage est construite. Une etude bibliographique et experimentale a permis de comparer prealablement differents materiaux: le filet a fourni la reponse la plus faib

APA, Harvard, Vancouver, ISO, and other styles

15

Nikzad, Dehaji Mohammad. "Structural Improvements of Convolutional Neural Networks." Thesis, Griffith University, 2021. http://hdl.handle.net/10072/410448.

Full text

Abstract:

Over the last decade, deep learning has demonstrated outstanding performance in almost every application domain. Among different types of deep frameworks, convolutional neural networks (CNNs), inspired by the biological process of the visual system, can learn to extract discriminative features from raw inputs without any prior manipulation. However, efficient information circulation and the ability to explore effective new features are still two key and challenging factors for a successful deep neural network. In this thesis, we aim at presenting novel structural improvements of the CNN framew

APA, Harvard, Vancouver, ISO, and other styles

16

Basu, Arindam. "Neural dynamics in reconfigurable silicon." Diss., Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/39542.

Full text

Abstract:

This work is a first step towards a long-term goal of understanding computations occurring in the brain and using those principles to make more efficient machines. The traditional computing paradigm calls for using digital supercomputers to simulate large scale brain-like neural networks resulting in large power consumption which limits scalability or model detail. For example, IBM's digital simulation of a cat brain with simplistic neurons and synapses consumes power equivalent to that of a thousand houses! Instead of digital methods, this work uses analog processing concepts to develop scala

APA, Harvard, Vancouver, ISO, and other styles

17

Elavarthi, Pradyumna. "Semantic Segmentation of RGB images for feature extraction in Real Time." University of Cincinnati / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1573575765136448.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Marti, Marco Ros. "Deep Convolutional Neural Network for Effective Image Analysis : DESIGN AND IMPLEMENTATION OF A DEEP PIXEL-WISE SEGMENTATION ARCHITECTURE." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-227851.

Full text

Abstract:

This master thesis presents the process of designing and implementing a CNN-based architecture for image recognition included in a larger project in the field of fashion recommendation with deep learning. Concretely, the presented network aims to perform localization and segmentation tasks. Therefore, an accurate analysis of the most well-known localization and segmentation networks in the state of the art has been performed. Afterwards, a multi-task network performing RoI pixel-wise segmentation has been created. This proposal solves the detected weaknesses of the pre-existing networks in the

APA, Harvard, Vancouver, ISO, and other styles

19

Sällqvist, Jessica. "Real-time 3D Semantic Segmentation of Timber Loads with Convolutional Neural Networks." Thesis, Linköpings universitet, Datorseende, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-148862.

Full text

Abstract:

Volume measurements of timber loads is done in conjunction with timber trade. When dealing with goods of major economic values such as these, it is important to achieve an impartial and fair assessment when determining price-based volumes. With the help of Saab’s missile targeting technology, CIND AB develops products for digital volume measurement of timber loads. Currently there is a system in operation that automatically reconstructs timber trucks in motion to create measurable images of them. Future iterations of the system is expected to fully automate the scaling by generating a volumetr

APA, Harvard, Vancouver, ISO, and other styles

20

Kothawade, Rohan Dilip. "Wine quality prediction model using machine learning techniques." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-20009.

Full text

Abstract:

The quality of a wine is important for the consumers as well as the wine industry. The traditional (expert) way of measuring wine quality is time-consuming. Nowadays, machine learning models are important tools to replace human tasks. In this case, there are several features to predict the wine quality but the entire features will not be relevant for better prediction. So, our thesis work is focusing on what wine features are important to get the promising result. For the purposeof classification model and evaluation of the relevant features, we used three algorithms namely support vector mach

APA, Harvard, Vancouver, ISO, and other styles

21

Schennings, Jacob. "Deep Convolutional Neural Networks for Real-Time Single Frame Monocular Depth Estimation." Thesis, Uppsala universitet, Avdelningen för systemteknik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-336923.

Full text

Abstract:

Vision based active safety systems have become more frequently occurring in modern vehicles to estimate depth of the objects ahead and for autonomous driving (AD) and advanced driver-assistance systems (ADAS). In this thesis a lightweight deep convolutional neural network performing real-time depth estimation on single monocular images is implemented and evaluated. Many of the vision based automatic brake systems in modern vehicles only detect pre-trained object types such as pedestrians and vehicles. These systems fail to detect general objects such as road debris and roadside obstacles. In s

APA, Harvard, Vancouver, ISO, and other styles

22

Rosenlew, Matilda, and Timas Ljungdahl. "Using Layer-wise Relevance Propagation and Sensitivity Analysis Heatmaps to understand the Classification of an Image produced by a Neural Network." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-252702.

Full text

Abstract:

Neural networks are regarded as state of the art within many areas of machine learning, however due to their growing complexity and size, a question regarding their trustability and understandability has been raised. Thus, neural networks are often being considered a "black-box". This has lead to the emersion of evaluation methods trying to decipher these complex networks. Two of these methods, layer-wise relevance propagation (LRP) and sensitivity analysis (SA), are used to generate heatmaps, which presents pixels in the input image that have an impact on the classification. In this report, t

APA, Harvard, Vancouver, ISO, and other styles

23

Mallu, Mallu. "Fashion Object Detection and Pixel-Wise Semantic Segmentation : Crowdsourcing framework for image bounding box detection & Pixel-Wise Segmentation." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-234691.

Full text

Abstract:

Technology has revamped every aspect of our life, one of those various facets is fashion industry. Plenty of deep learning architectures are taking shape to augment fashion experiences for everyone. There are numerous possibilities of enhancing the fashion technology with deep learning. One of the key ideas is to generate fashion style and recommendation using artificial intelligence. Likewise, another significant feature is to gather reliable information of fashion trends, which includes analysis of existing fashion related images and data. When specifically dealing with images, localisation

APA, Harvard, Vancouver, ISO, and other styles

24

Montavon, Grégoire Verfasser], Klaus-Robert [Akademischer Betreuer] [Müller, Yoshua [Akademischer Betreuer] Bengio, and Léon [Akademischer Betreuer] Bottou. "On layer-wise representations in deep neural networks / Grégoire Montavon. Gutachter: Klaus-Robert Müller ; Yoshua Bengio ; Léon Bottou. Betreuer: Klaus-Robert Müller." Berlin : Technische Universität Berlin, 2013. http://d-nb.info/1065665458/34.

Full text

APA, Harvard, Vancouver, ISO, and other styles

25

Malý, Ondřej. "Detekce zahalených tváří v obraze." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2020. http://www.nusl.cz/ntk/nusl-413097.

Full text

Abstract:

The aim of this work is to study and test current methods for face detection on veiled faces and evaluate the results. In the first chapter, five selected methods are theoretically analyzed and in the second chapter the individual methods are evaluated, both for the Wider Face file and for the actual set of photos with veiled faces. Subsequently, the Dlib CNN method is improved for better detection of veiled faces and reprogrammed to detect the degree of veil from the tested image

APA, Harvard, Vancouver, ISO, and other styles

26

Shaban, Hassan. "Experimental Investigations of Internal Air-water Flows." Thesis, Université d'Ottawa / University of Ottawa, 2015. http://hdl.handle.net/10393/32952.

Full text

Abstract:

The objective of the present thesis research is to apply state-of-the-art experimental and data analysis techniques to the study of gas-liquid pipe flows, with a focus on conditions occurring in header-feeder systems of nuclear reactors under different accident scenarios. Novel experimental techniques have been proposed for the identification of the flow regime and measurement of the flow rates of both phases in gas-liquid flows. These techniques were automated, non-intrusive and economical, which ensured that their use would be feasible in industrial as well as laboratory settings. Measuremen

APA, Harvard, Vancouver, ISO, and other styles

27

Radhakrishnan, Aswathnarayan. "A Study on Applying Learning Techniques to Remote Sensing Data." The Ohio State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1586901481703797.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Osman, Ousama. "Méthodes de diagnostic en ligne, embarqué et distribué dans les réseaux filaires complexes." Thesis, Université Clermont Auvergne‎ (2017-2020), 2020. http://www.theses.fr/2020CLFAC038.

Full text

Abstract:

Les recherches menées dans cette thèse portent sur le diagnostic de réseaux filaires complexes à l’aide de la réflectométrie distribuée. L’objectif est de développer de nouvelles technologies de diagnostic en ligne, distribuées des réseaux complexes permettant la fusion de données ainsi que la communication entre les réflectomètres pour détecter, localiser et caractériser les défauts électriques (francs et non francs). Cette collaboration entre les réflectomètres permet de résoudre le problème d’ambiguïté de localisation des défauts et d’améliorer la qualité du diagnostic. La première contribu

APA, Harvard, Vancouver, ISO, and other styles

29

Savan, Emanuel-Emil. "Consumer liking and sensory attribute prediction for new product development support : applications and enhancements of belief rule-based methodology." Thesis, University of Manchester, 2015. https://www.research.manchester.ac.uk/portal/en/theses/consumer-liking-and-sensory-attribute-prediction-for-new-product-development-support-applications-and-enhancements-of-belief-rulebased-methodology(0582be52-a5ce-47da-836d-e30b5506fb41).html.

Full text

Abstract:

Methodologies designed to support new product development are receiving increasing interest in recent literature. A significant percentage of new product failure is attributed to a mismatch between designed product features and consumer liking. A variety of methodologies have been proposed and tested for consumer liking or preference prediction, ranging from statistical methodologies e.g. multiple linear regression (MLR) to non-statistical approaches e.g. artificial neural networks (ANN), support vector machines (SVM), and belief rule-based (BRB) systems. BRB has been previously tested for con

APA, Harvard, Vancouver, ISO, and other styles

30

Soudani, Azeddine. "Application des réseaux de neurones aux mesures simultanées en écoulement turbulent." Grenoble INPG, 1996. http://www.theses.fr/1996INPG0180.

Full text

Abstract:

Une nouvelle methode pour le depouillement des etalonnages des sondes thermo-anemometriques a fil et film chauds, est employee pour les mesures simultanees de vitesses et de densite dans un ecoulement turbulent. La methode est fondee sur une application specifique des reseaux de neurones. Il s'agit de reseaux du type perceptron multicouches ayant pour regle d'apprentissage, l'algorithme de la retropogation d'erreur. Cette methode auto-adaptative a ete appliquee aux etalonnages de deux types de sonde. Elle donne une meilleure precision sur la reduction des etalonnages que les methodes classique

APA, Harvard, Vancouver, ISO, and other styles

31

Sadli, Rahmad. "Étude et développement d'un dispositif routier d'anticollision basé sur un radar ultra large bande pour la détection et l'identification notamment des usagers vulnérables." Thesis, Valenciennes, 2019. http://www.theses.fr/2019VALE0005.

Full text

Abstract:

Dans ce travail de thèse, nous présentons nos travaux qui portent sur l’identification des cibles en général par un radar Ultra-Large Bande (ULB) et en particulier l’identification des cibles dont la surface équivalente radar est faible telles que les piétons et les cyclistes. Ce travail se décompose en deux parties principales, la détection et la reconnaissance. Dans la première approche du processus de détection, nous avons proposé et étudié un détecteur de radar ULB robuste qui fonctionne avec des données radar 1-D (A-scan) à une dimension. Il exploite la combinaison des statistiques d’ordr

APA, Harvard, Vancouver, ISO, and other styles

32

Fang, Chieh-Ning, and 方婕寧. "Wide and Deep Neural Network for Image Recognition." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/58512958860467648923.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

(5930585), Vineeth Chigarangappa Rangadhamap. "Fast Computation of Wide Neural Networks." Thesis, 2019.

Find full text

Abstract:

<div>The recent advances in articial neural networks have demonstrated competitive performance of deep neural networks (and it is comparable with humans) on tasks like image classication, natural language processing and time series classication. These large scale networks pose an enormous computational challenge, especially in resource constrained devices. The current work proposes a targeted-rank based framework for accelerated computation of wide neural networks. It investigates the problem of rank-selection for tensor ring nets to achieve optimal network compression. When applied to a state

APA, Harvard, Vancouver, ISO, and other styles

34

Wang, Kuan-Cheng, and 王冠程. "Click Through Rate Prediction Using Character-level Wide and Deep Convolutional Neural Network." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/26s46h.

Full text

Abstract:

碩士<br>國立交通大學<br>多媒體工程研究所<br>106<br>The Internet consolidated itself as a very powerful platform that has changed the way we do business, and the way we communicate. As more users are used to the Internet, online advertising is one of the most effective ways for businesses of all sizes to expand their reach, find new customers, and diversify their revenue streams. Real-time bidding (RTB) is a programmatic auction that allows the advertising inventory to be bought and sold on a per-impression basis. To achieve the highest profits for advertisers in RTB, it is an important issue to formulate a g

APA, Harvard, Vancouver, ISO, and other styles

35

Chen, Sheng-Sing, and 陳勝興. "An Application of Neural-Network-Based Visual Servoing System to Image Path Marking and Precision Seam Welding with Wide Strip Image." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/c68f66.

Full text

Abstract:

碩士<br>南臺科技大學<br>機械工程系<br>106<br>In this study, we aim at developing a Neural-Network-Based Visual Servoing system to carry out Laser welding for irregular weld joint profiles. We propose an image processing scheme capable of visually tracking the weld seam and providing a good estimate on the weld gaps. The resulting image information is then displayed on the monitor. The estimate is also converted into CAM command through the Neural-Network Visual Servoing system to perform Laser welding and make a dynamical adjustment for the Laser spot size. A X-Y-Zoom servo table equipped with machine visi

APA, Harvard, Vancouver, ISO, and other styles

36

Kao, Wan-Ching, and 高婉晴. "Optimization of LED wire bonding process parameters based on neural network." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/rg9twp.

Full text

Abstract:

碩士<br>中原大學<br>工業與系統工程研究所<br>107<br>In the LED packaging process, the wire bonding technology is one of the key processes, and the poor quality of the process will directly affect the functionality of the product, resulting in the cost of the previous process input being scrapped. In order to improve product quality stability and production yield, the monitoring and management of the wire bonding process have always been a key management project for many manufacturers. In this study, a systematic solution to the optimization of the process parameters of the LED package wire is proposed. Firstly

APA, Harvard, Vancouver, ISO, and other styles

37

Chen, Lih-Shen, and 陳勵生. "Neural Network Application for Equipment Parameter Setting: Using Wire Bonder as an Example." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/56024062914990579096.

Full text

Abstract:

碩士<br>國立清華大學<br>工業工程與工程管理學系<br>88<br>Because of the great physical complexity of the precision equipment used in semiconductor manufacturing , it is very difficult to mathematically model the machine behaviors for equipment parameter setting. Trial - and - errors and/or several runs of DOE (Design of Experiment) are often needed in equipment parameter settings for new product production. This research attempts to use Neural Network to model the machine behaviors in order to provide an approach for machine parameter setting thus eliminating or reducing the wasted materials, time, and other reso

APA, Harvard, Vancouver, ISO, and other styles

38

Kao, Ming-Yi, and 高明義. "The Suppression of Deterioration in Wire Electrical Discharge Machining Process by Neural Network." Thesis, 1996. http://ndltd.ncl.edu.tw/handle/10764871901811968955.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Chen, Yu-Min, and 陳幼敏. "Detection and Suppression of Deterioration in Wire Electrical Discharge Machining Process by Neural Network." Thesis, 1997. http://ndltd.ncl.edu.tw/handle/05204797886627941055.

Full text

Abstract:

碩士<br>國立臺灣大學<br>機械工程學系<br>85<br>Improvement of the machining speed of wire electrical discharge machining(WEDM) process under various machining conditions is studied. Neural network is employed to monitor the degree of deterioration of the process includingwire rupture and back-stroke of the feed. Pulse on time, total sparking frequency, and abnormal ratio defined as the ratio of the total numbers ofthe abnormal sparks to the total numbers of the sparks in a sampling periodare chosen as the

APA, Harvard, Vancouver, ISO, and other styles

40

Syu-ShengLi and 李旭昇. "Application of Neural Network on the Optimization of Wire Sweep for IC Packaging Process." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/ku737f.

Full text

Abstract:

碩士<br>國立成功大學<br>機械工程學系<br>107<br>In electronic packaging, molding encapsulates a package to protect the integrated circuit chips and wires from environmental or mechanical damages. During molding, defects like wire sweep may occur. Gold wires are common components in integrated circuit IC packages to transfer electronic signals between the die and the lead-frame contacts. Number-increased I/Os are built with more wires and smaller wire gaps increasing wire sweep problems. Earlier, experienced engineers solved these problems through trial and error requiring a large number of molding experiment

APA, Harvard, Vancouver, ISO, and other styles

41

Tsai, Dai-rong, and 蔡岱蓉. "The Application of Grey Relational Analysis and Neural Network Learning On IC Wire Bond Packaging Quantity." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/75507989335843706278.

Full text

Abstract:

碩士<br>義守大學<br>工業工程與管理學系碩士班<br>97<br>Prevalently fierce competition in business environment, the decision making of executive will directly determine the development of one enterprise. However, there are myriad uncertainties even from the predictable future for each business establishment. It’s always an important task for an entrepreneur on how to precisely predict the future trend and making correct decision for the enterprise. The objective of this research has aimed to setup a more accurate prediction system which can be used to forecast production output, to increase the elasticity of supp

APA, Harvard, Vancouver, ISO, and other styles

42

Fan, Chen-Lun, and 范振倫. "Surface Roughness Prediction based on Markov Chain and Deep Neural Network for Wire Electrical Discharge Machining." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/24zse3.

Full text

Abstract:

碩士<br>國立中央大學<br>資訊工程學系<br>107<br>Industry 4.0 Smart Manufacturing is a hot topic recently. Today's global manufacturing industry is committed to smart manufacturing through industrial Internet of Things, big data analytics, and Cyber Physical System (CPS) technologies to improve product performance and product quality by saving production time and cost. This paper explores Virtual Metrology (VM) research to predict product quality before or after the production process has not been completed, without the need of product measurement. Specifically, this paper focuses on the Surface Roughness pre

APA, Harvard, Vancouver, ISO, and other styles

43

Tsao, Chih-Chiang, and 曹志強. "The Taguchi Method and Neural Network Analysis in a Loop of Wire Bonding Profile for I.C. Packaging." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/49111436032721865159.

Full text

Abstract:

碩士<br>國立成功大學<br>機械工程學系<br>88<br>The linkage-spring model has been used to determine the design rules to reduce the loop heights and the sagging of gold wire in the package. The purpose of this thesis is to simulate the capillary trajectory from the first bond to the second bond stages by a modified linkage-spring model including a looping speed factor. Also, the looping speed effects on the wirebond profiles due to the inertia mass and the change of material properties in different strain-rates have been studied in this thesis. At the same time, Taguchi method was used for the robu

APA, Harvard, Vancouver, ISO, and other styles

44

Chang, Hung-Zhi, and 張鴻志. "Using Neural Networks and Immune Algorithms to Find the Optimal Parameters for IC Wire Bonding Processes." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/87731192832536559968.

Full text

Abstract:

碩士<br>國立雲林科技大學<br>工業工程與管理研究所碩士班<br>93<br>The wire bonding process is the key process in an IC chip-package. It is an urgent problem for IC chip-package industry to improve the wire bonding process capability. In this study, an application of artificial neural networks (ANN) and artificial immune systems (AIS) is proposed to optimize parameters in the wire bonding process in order to achieve highly level performance and quality. In this research, the algorithm of AIS with memory cell and suppressor cell mechanisms is developed, and two new algorithms are proposed：Multiple-Objectives Immume Algo

APA, Harvard, Vancouver, ISO, and other styles

45

Wei-ChungTseng and 曾微中. "Layer-wise Fixed Point Quantization for Deep Convolutional Neural Networks and Implementation of YOLOv3 Inference Engine." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/x46nq6.

Full text

Abstract:

碩士<br>國立成功大學<br>電腦與通信工程研究所<br>107<br>With the increasing popularity of mobile devices and the effectiveness of deep learning-based algorithms, people try to put deep learning models on mobile devices. However, it is limited by the complexity of computational and software overhead. We propose an efficient framework for inference to fit resource-limited devices with about 1000 times smaller than Tensorflow in code size, and a layer-wised quantization scheme that allows inference computed by fixed-point arithmetic. The fixed-point quantization scheme is more efficient than floating point arithmet

APA, Harvard, Vancouver, ISO, and other styles

46

Lu, Hsiu-Chen, and 盧脩塵. "Displacement Analysis of a Two-Wire-Driven Continuum Robot with a Contacted Obstacle based on Neural Network Model." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/53vy75.

Full text

Abstract:

碩士<br>國立臺灣科技大學<br>機械工程系<br>106<br>Continuum robot becomes more and more popular in recent years. Displacement analysis is necessary to find the position of continuum robots. In robot control, there are a lot of researches on path planning and how to bypass the obstacle. There are also many methods can be used to analyze the displacement of continuum robots like geometry models and beam theory models. These methods can also solve the kinematics problem about continuum robot with end loads. However, there is no research about what will happen when a continuum robot contacts an obstacle and keep

APA, Harvard, Vancouver, ISO, and other styles

47

Ming, Wang Chung, and 王崇銘. "Application of a Combined Self-organizing Fuzzy Controller and Neural-network-based Disturbance Observe in Wire Tension Control of a Micro Wire-EDM Machine." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/68721259279302922040.

Full text

Abstract:

碩士<br>華梵大學<br>機電工程學系博碩專班<br>98<br>As growing demands on machining accuracy and miniaturization in the variety of manufacturing industries, micro wire-EDM has been one of key technologies for micromachining. However, wire bending and vibration are prone to occur due to unexpected disturbance of wire transport system, discharge forces and flushing pressure during machining and thereby leading to machining inaccuracy. Therefore, wire tension should be controlled tightly when the wire transport system is subject to undesired disturbance for the geometrical accuracy of micro wire-EDM. This paper pr

APA, Harvard, Vancouver, ISO, and other styles

48

Hsien, Kuei, and 陳桂嫻. "Application of Neural Network and Tabu Search to Find the Optimal Parameter of Wire Bonding Process in Semiconductor Packaging." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/23297561929399719194.

Full text

Abstract:

碩士<br>國立雲林科技大學<br>工業工程與管理研究所碩士班<br>91<br>With the prosperous development of high tech industry, the trend for electronics products not only has to be light, slimmer, and small, but also has to be multi-functional. The impact of this trend on the semiconductor industry is the in the increase in chip number and wafer size, and decrease in gate length. Therefore, the high density and high pincounts are required in the IC assembly process. In response to this trend, the wire bonding process of IC assembly has to apply the high precision wire bonding technology with fine pitch, and the 50 μm pad pi

APA, Harvard, Vancouver, ISO, and other styles

49

Ho, Chen-Sung, and 何楨松. "Application of Neural Networks in the IC package to enhance the quality of the copper wire bonding process." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/87398379544364321472.

Full text

Abstract:

碩士<br>國立高雄應用科技大學<br>工業工程與管理系碩士班<br>102<br>Wire bonders make up the most percentage of equipments in an IC packaging plant, and the costs of gold wires, or the raw material used by wire bonders, are largely affected by gold prices in the international market. To lower the production cost, all professional IC packaging plants are highly motivated to replace gold wires with cooper wires. However, due to differences in material characteristics, such replacement is not easy, as the production quality and efficiency are highly affected by the capacity of the wire bonders, process conditions and para

APA, Harvard, Vancouver, ISO, and other styles

50

Chen, Yen-Cheng, and 陳彥呈. "Combining Fuzzy Theory, Neural Networks and Genetic Algorithms to Find the Optimal Parameter – Take the Process of Wire Bonding in Semiconductor Packaging as Example." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/andc69.

Full text

Abstract:

碩士<br>國立雲林科技大學<br>工業工程與管理系<br>104<br>Taguchi method is most frequently used in Parameter Design. However Taguchi method is not be able to apply in the variety of parameters design problem. Based on the above issue, this research proposes a new method to find the optimal process parameters for the relevant cases. First fuzzy theory is applied to transform the Taguchi orthogonal array experimental data. Second the back propagation neural network is used for training the model. Finally the Genetic Algorithm and the Fuzzy Genetic Algorithm were applied to find the Optimal Parameter. We compare the

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!