Rozprawy doktorskie na temat „Artificial neural network”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych rozpraw doktorskich naukowych na temat „Artificial neural network”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj rozprawy doktorskie z różnych dziedzin i twórz odpowiednie bibliografie.
BRUCE, WILLIAM, i 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.
Pełny tekst źródłaDenna 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.
Смаль, Богдан Віталійович. "Artificial Neural Network". Thesis, Київський національний університет технологій та дизайну, 2017. https://er.knutd.edu.ua/handle/123456789/7384.
Pełny tekst źródłaChambers, Mark Andrew. "Queuing network construction using artificial neural networks /". The Ohio State University, 2000. http://rave.ohiolink.edu/etdc/view?acc_num=osu1488193665234291.
Pełny tekst źródłaLeija, 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.
Pełny tekst źródłaAlkharobi, Talal M. "Secret sharing using artificial neural network". Diss., Texas A&M University, 2004. http://hdl.handle.net/1969.1/1223.
Pełny tekst źródłaZhao, 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.
Pełny tekst źródłaParzhin, Yu, А. Rohovyi i V. Nevliudova. "Detector Artificial Neural Network. Neurobiological rationale". Thesis, ХНУРЕ, 2019. http://openarchive.nure.ua/handle/document/10037.
Pełny tekst źródłaNg, Justin. "Artificial Neural Network-Based Robotic Control". DigitalCommons@CalPoly, 2018. https://digitalcommons.calpoly.edu/theses/1846.
Pełny tekst źródłaKhazanova, Yekaterina. "Experiments with Neural Network Libraries". University of Cincinnati / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1527607591612278.
Pełny tekst źródłaLukashev, A. "Basics of artificial neural networks (ANNs)". Thesis, Київський національний університет технологій та дизайну, 2018. https://er.knutd.edu.ua/handle/123456789/11353.
Pełny tekst źródłaBrunger, 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.
Pełny tekst źródłaTang, 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.
Pełny tekst źródłaTupas, 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.
Pełny tekst źródłaLuan, Wenpeng. "Voltage ranking using artificial neural network method". Thesis, University of Strathclyde, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.366960.
Pełny tekst źródłaBataineh, Mohammad Hindi. "Artificial neural network for studying human performance". Thesis, University of Iowa, 2012. https://ir.uiowa.edu/etd/3259.
Pełny tekst źródłaChoi, Hyunjong. "Medical Image Registration Using Artificial Neural Network". DigitalCommons@CalPoly, 2015. https://digitalcommons.calpoly.edu/theses/1523.
Pełny tekst źródłaBaker, Thomas Edward. "Implementation limits for artificial neural networks". Full text open access at:, 1990. http://content.ohsu.edu/u?/etd,268.
Pełny tekst źródłaCottens, Pablo Eduardo Pereira de Araujo. "Development of an artificial neural network architecture using programmable logic". Universidade do Vale do Rio dos Sinos, 2016. http://www.repositorio.jesuita.org.br/handle/UNISINOS/5411.
Pełny tekst źródłaMade available in DSpace on 2016-06-29T14:42:16Z (GMT). No. of bitstreams: 1 Pablo Eduardo Pereira de Araujo Cottens_.pdf: 1315690 bytes, checksum: 78ac4ce471c2b51e826c7523a01711bd (MD5) Previous issue date: 2016-03-07
Nenhuma
Normalmente Redes Neurais Artificiais (RNAs) necessitam estações de trabalho para o seu processamento, por causa da complexidade do sistema. Este tipo de arquitetura de processamento requer que instrumentos de campo estejam localizados na vizinhança da estação de trabalho, caso exista a necessidade de processamento em tempo real, ou que o dispositivo de campo possua como única tarefa a de coleta de dados para processamento futuro. Este projeto visa criar uma arquitetura em lógica programável para um neurônio genérico, no qual as RNAs podem fazer uso da natureza paralela de FPGAs para executar a aplicação de forma rápida. Este trabalho mostra que a utilização de lógica programável para a implementação de RNAs de baixa resolução de bits é viável e as redes neurais, devido à natureza paralelizável, se beneficiam pela implementação em hardware, podendo obter resultados de forma muito rápida.
Currently, modern Artificial Neural Networks (ANN), according to their complexity, require a workstation for processing all their input data. This type of processing architecture requires that the field device is located somewhere in the vicintity of a workstation, in case real-time processing is required, or that the field device at hand will have the sole task of collecting data for future processing, when field data is required. This project creates a generic neuron architecture in programmabl logic, where Artifical Neural Networks can use the parallel nature of FPGAs to execute applications in a fast manner, albeit not using the same resolution for its otputs. This work shows that the utilization of programmable logic for the implementation of low bit resolution ANNs is not only viable, but the neural network, due to its parallel nature, benefits greatly from the hardware implementation, giving fast and accurate results.
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.
Pełny tekst źródłaXu, Shuxiang. "Neuron-adaptive neural network models and applications /". [Campbelltown, N.S.W. : The Author], 1999. http://library.uws.edu.au/adt-NUWS/public/adt-NUWS20030702.085320/index.html.
Pełny tekst źródłaBeckenkamp, Fábio Ghignatti. "A component architecture for artificial neural network systems". [S.l. : s.n.], 2002. http://deposit.ddb.de/cgi-bin/dokserv?idn=964923580.
Pełny tekst źródłaLeong, Cheok Fan. "Approximation theory of multilayer feedforward artificial neural network". Thesis, University of Macau, 2002. http://umaclib3.umac.mo/record=b1446728.
Pełny tekst źródłaTheramongkol, 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.
Pełny tekst źródłaZahra, 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.
Pełny tekst źródłaThirkell, Lawrence Alexander. "An artificial neural network approach to authorship determination". Thesis, Heriot-Watt University, 1993. http://hdl.handle.net/10399/1418.
Pełny tekst źródłaJohnson, D. E. "Analogue VLSI implementation of an artificial neural network". Thesis, University of Liverpool, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.367276.
Pełny tekst źródłaKannemeyer, Johan Etienne. "Artificial neural network decoding of multi-h CPM". Master's thesis, University of Cape Town, 1997. http://hdl.handle.net/11427/19638.
Pełny tekst źródłaChan, Kwok Hung Billy Carleton University Dissertation Engineering Mechanical and Aerospace. "Predicting weld features using artificial neural network technology". Ottawa, 1996.
Znajdź pełny tekst źródłaMryyan, Mahmoud. "Environmental site characterization via artificial neural network approach". Diss., Manhattan, Kan. : Kansas State University, 2008. http://hdl.handle.net/2097/1120.
Pełny tekst źródłaWu, Chung-Yu. "Predicting water table fluctuations using artificial neural network". College Park, Md.: University of Maryland, 2008. http://hdl.handle.net/1903/8826.
Pełny tekst źródłaThesis research directed by: Fischell Dept. of Bioengineering . Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
Dario, Ugo <1986>. "Forecasting energy market: an artificial neural network approach". Master's Degree Thesis, Università Ca' Foscari Venezia, 2015. http://hdl.handle.net/10579/5810.
Pełny tekst źródłaKeisala, Simon. "Designing an Artificial Neural Network for state evaluation in Arimaa : Using a Convolutional Neural Network". Thesis, Linköpings universitet, Artificiell intelligens och integrerade datorsystem, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-143188.
Pełny tekst źródłaLind, Benjamin. "Artificial Neural Networks for Image Improvement". Thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-137661.
Pełny tekst źródłaÅström, 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.
Pełny tekst źródłaTracy, Justin. "Prediction of wind speeds with an artificial neural network". Click here to view, 2010. http://digitalcommons.calpoly.edu/eesp/24/.
Pełny tekst źródłaProject advisor: Xiao-Hua Yu. Title from PDF title page; viewed on Apr. 20, 2010. Includes bibliographical references. Also available on microfiche.
Xu, Le Yan. "Artificial neural network short-term electrical load forecasting techniques". Thesis, University of Macau, 1999. http://umaclib3.umac.mo/record=b1445624.
Pełny tekst źródłaZeng, Shi-Ran, i 曾世任. "Artificial Neural Network for Image Recognition". Thesis, 2011. http://ndltd.ncl.edu.tw/handle/87588825955623867932.
Pełny tekst źródła國立高雄海洋科技大學
電訊工程研究所
99
Biometrics is a common topic. In this field, neural network is a common machine learning algorithm, and it has been applied to many fields. Recently, support vector machines (referred to as SVM) which is based on statistical learning theory catches the most attention. It is because SVM has the better recognition capability and faster calculation speed than the general neural networks; furthermore, it does not have the situation of over-learning. There are many researches proving that SVM has good performance of recognition in the open literature. Probabilistic neural network (referred to as PNN) is a kind of neural network based on Bayesian decision theory, and it belongs to the feedforward network architecture. PNN is highly regarded due to its short training time, and also, it does not have the iterative process. In this thesis, we apply in human face recognition and Traditional Chinese handwriting recognition. Most researches use the public face databases in human face recognition. For example, they are ORL, Yale, INDIAN, etc. Thus, we use data source both from ORL and the database created by ourselves in this study. In handwriting, the database was made of 20 persons handwriting in Traditional Chinese. In this study, we consider individual handwriting habits use different quantitative methods to explore the feasibility of using handwriting recognition as an identification identity. The experimental results show that the recognition rate by using SVM and ORL is 96%, while the recognition rate for our database is 92%(Block Background) and 80%(White Background) respectively. In Traditional Chinese handwriting, the best rate of using SVM to recognize is 75%, while the best rate for PNN is 80%.
Hwang, Yih-Shyan, i 黃議賢. "Password Authentication Using Artificial Neural Network". Thesis, 1994. http://ndltd.ncl.edu.tw/handle/00101971263020082688.
Pełny tekst źródła國立中興大學
應用數學研究所
82
In this dissertation, a password authentication scheme based on artificial neural network model with modified perceptron algorithm and a strong cryptographic operation such as DES(data encryption standard) is proposed. Because of parallel computing characteristics of artificial neural network, the scheme can quickly and efficiently respond to any login attempt. Thus, it is suitable for real-time service. Moreover, each user is completely free to choose his own identifier and password. Because those identifiers and passwords in the system are combined together, any illegal modification by the intruder to the weight matrices in the artificial neural network will influence the others and can easily be detected. Furthermore, after a new user is inserted into the system, it needs only to add few terms of the former weight matrices. Therefore, our scheme is suitable for practical implementation.
Su, chutin, i 蘇祝鼎. "Artificial Neural Network for Dipole Localization". Thesis, 1997. http://ndltd.ncl.edu.tw/handle/64838032357715825842.
Pełny tekst źródła國立交通大學
控制工程系
85
In this thesis, we use the neural networks to deal with the problem of dipole localization. We aim at estimating location, orientation, and moment strength of a single dipole which induces epilepsy in human brain. The inverseproblem is a highly nonlinear approximation process. We applied current dipolemodel to generate the brain electrical potential distribution on the scalp. The dipole and its corresponding brain potentials were used as training patternsfor the neural networks. A neural network trained to learn correspondence of dipoles to brain potential distribution can be used to estimate the dipole''slocation, orientation, and moment strength. It will be useful for clinicalapplications. In this reasearch, we investigatedthe cppability of neural network in dipole localization. The performance of the neural network depends on region of dipole localization andorientation of dipole moment. we also studied the effect of noise interferencefor the performance of neural network. We found that the accuracy of dipole localization decreased as the signal-to-noise ratio was poor. In addition, we proposed a model of hybrid network . Compared with the conventional multi-layer perceptrons network, the hybri d network indeed requires less training time and achieves better localization results. It might be a feasible neural network model for dipole localization.
Chen, You-Yu, i 陳宥諭. "DOA Estimation with Artificial Neural Network". Thesis, 2019. http://ndltd.ncl.edu.tw/handle/2pxvzy.
Pełny tekst źródła國立交通大學
電信工程研究所
107
A uniform linear array can receive multiple unequal power signals coming from different direction-of-arrival (DOA). This thesis considers DOA estimation with artificial neural network (NN). Conventional NN approaches are not effective for the unequal-power scenario. Also, the computational complexity is very high. Incorporating signal processing techniques, we propose two NNs to solve the problems. The first NN divides the estimation range into sectors, and consists of a spatial filter and a classifier. With a rotation operation, a spatial filter and a classifier can be used for all sectors, significantly reducing the training time and computational complexity. The second NN uses the same sector-based processing structure. However, the spatial filter is replaced with a power detector. With a frequency-domain nulling operation, only a power detector and a classifier are needed for all sectors. The computational complexity of the second NN can be further reduced. Simulation results show that the performance of the proposed NNs can outperform the well-known MUSIC algorithm under low SNR. Also, the computational complexity can also be lower than that of MUSIC.
SINGH, ASHISH KUMAR. "RAINFALL FORECASTING USING ARTIFICIAL NEURAL NETWORK". Thesis, 2016. http://dspace.dtu.ac.in:8080/jspui/handle/repository/15552.
Pełny tekst źródłaGuha, Devi Rani. "Artificial Neural Network Based Channel Equalization". Thesis, 2011. http://ethesis.nitrkl.ac.in/2081/1/devi-thesis-corrected.pdf.
Pełny tekst źródłaXue, Kuo Qiang, i 薛國強. "An intelligent sales forecasting system through artificial neural networks and fuzzy neural network". Thesis, 1996. http://ndltd.ncl.edu.tw/handle/07455980576654976365.
Pełny tekst źródłaLin, Tz-tsau, i 林子超. "Structural Damage Detection using Artificial Neural Network". Thesis, 1997. http://ndltd.ncl.edu.tw/handle/61054947437243824323.
Pełny tekst źródła國立成功大學
航空太空工程學系
85
This thesis presents an approach based on the artificial neural network to detect damages in a structure. By using the modal information of a structure before and after damage, we construct an artificial neural network model.The neural network is trained by examples which simulate various cases of structural damage using the finite element model of the structural system. The objective is to detect possible damage, including both extent and location,in the structure. Validity of the proposed approach is confirmed by using simulated examples in which the effect of noise and incomplete mode are included.
Lin, I.-Chih, i 林奕志. "Infrared Face Recognition Using Artificial Neural Network". Thesis, 2004. http://ndltd.ncl.edu.tw/handle/70053617787203072670.
Pełny tekst źródła國立高雄第一科技大學
電腦與通訊工程所
92
This research aims at the construction of an infrared face recognition system. Although the development of the visible face recognition system has been developed for many years, as well as many other recognition algorithms, the performance is not satisfactory, due to several environmental distracters, such as light, the instruments, which bring about the problems of feature extraction. However, as far as this infrared face recognition system is concerned, based on the heat radiation of the human body, the final extracted information is the actual temperature which would not be affected by light, for example. And that is one of the advantages of the use of infrared images, which draws increasing attention for further studies. The employment of the infrared face recognition system which would not be affected by light is proven successfully. Also, the infrared image of different targets cannot be counterfeited. Hence, the performance of the infrared face recognition is regarded more effective than that of the visible face recognition system. In practice, due to the high expense of the infrared machine plus the serious noise problem and its poor resolution, the infrared face recognition system is currently under further research and development. In this thesis, the employment of a new technique in the infrared face recognition field is studied, with the comparison and contrast between the performances of the new analysis and the traditional analysis. The first part of this thesis is to introduce the methods for the image pre-process and the face clip. In the face clip, two methods to clip the two different kinds of the face images from the background are illustrated. Some adjustments are in particular made for the clipped face images as the preparation for the next discussion. Secondly, three kinds of analysis methods in the feature extraction stage are executed. Because of the resolution limits of the infrared machine, even though the temperature accuracy of the machine can achieve hundredth, there are still several problems in the facial feature extraction. In other words, the visible face recognition, used for the homely facial feature extraction, is not as practical for infrared image. With different targets, the facial features of the persons may not be successfully extracted as expected. So, as far as feature extraction is concerned, the entire face image is discussed other than the local feature extraction. The third part is the construction of the recognition system. In this thesis, the “Plastic Perceptron” to classify different people is used. In the traditional neural network, if the user wants to add the new extracted facial information into the recognition system, the entire neural network should be retrained. But now, it is not necessary when employing the Plastic Perceptron. Therefore, the Plastic Perceptron is regarded as more suitable for face recognition.
Horng, Yu Jing, i 洪毓鈞. "Process Optimization via an Artificial Neural Network". Thesis, 1995. http://ndltd.ncl.edu.tw/handle/61356944221656412222.
Pełny tekst źródła逢甲大學
化學工程研究所
83
In this thesis, we consider the issue of applying neural network to the process optimization problem and robust controller design problem. The objective function of unconstrainted optimization problem can be mapped on to the energy function of the artificail neural network(ANN)in a direct way, and the network will find the minimum by obeying its own dynamics. For the optimization problem with constraints, we used the augmented Lagrange multiplier method to transform problem into a problem in which a single unconstrainted function is minimized, then we found the answer by the same step. As for the robust controller design problem, we applied the idea of Rotstein et al. to formulate the robust characteristic polynomial assignment problem as an optimization problem subject to linear constraints with uncertainty, at last we attained the controller by the same methods of optimization function with constraints. In order to prove the ability of artificial neural network and the affection of parameters, we tested several examples, the result was satisfactory and robust controller was better than the result of literature.
WANG, YOU-REN, i 王祐人. "Artificial neural network for digits pattern recognition". Thesis, 1991. http://ndltd.ncl.edu.tw/handle/09177770124098150633.
Pełny tekst źródłaGau, Peng-wei, i 高鵬惟. "Image Fusion Algorithm using Artificial Neural Network". Thesis, 2009. http://ndltd.ncl.edu.tw/handle/85802827401493351920.
Pełny tekst źródła義守大學
資訊工程學系碩士班
97
The wavelength of visible light is between 0.4~0.7μm which is also the range of most electro-optical device. However, in additional to visible lights, there are many other devices providing useful information hidden in a variety of wavelength. Among those applications, infrared information is most widely used. Infrared information essentially responds the thermal information of objects in the scene. One of its unique features is that visible sensors see nothing in the night while the infrared sensors see things such as animals and buildings, which emit “hot”. Since visible information and infrared information provide the complementary features, it is reasonable to fuse the two signals to see more things in different weather and background situations. This thesis proposes an image fusion algorithm by using artificial neural network which combines the visible and the infrared images together to obtain complementary and useful information. By adjusting appropriate fusion parameters, we can obtain the fused image with better quality.
Wang, Chen-Kuei, i 王珍貴. "Simulating Typhoon Rainfall with Artificial Neural Network". Thesis, 2007. http://ndltd.ncl.edu.tw/handle/68782924427622053889.
Pełny tekst źródła國立成功大學
水利及海洋工程學系碩博士班
95
Typhoon brought abundant rainfall on its covering area along moving path. The characteristics of typhoon itself and local terrain and meteorological factors of a gage station affect the amount of rainfall. It is difficult to estimate the real-time rainfall depth of typhoon because the relationship between rainfall and related factors is non-linear and interact. In this thesis, a Back-Propagation Artificial Neural Network model (BPN) was adopted to simulate and forecast rainfall. This model could imitate the complicated non-linear behavior of rainfall process of typhoon. Rainfall and typhoon data of 18 typhoons of Tsengwen gage station were collected for case study. This thesis selected the data of 14 typhoons for model calibration and 4 for validation. There were 17 factors in total for model input. They could be divided into two categories. One was typhoon’s property which included position of typhoon center, wind velocity, atmospheric pressure and radius of grade 7 wind. The other was the characteristic factors of gage station. These were local wind velocity, temperature and topographic parameters. There are two types of BPN models developed in this thesis. The model had two hidden layers to increase the ability of description. One layer had 5 processing elements and the other had 2 processing elements. By properly adjusting the values of axon weighting and neuron bias, the BPN model could memorize the physical mechanism of the process of typhoon’s rainfall. Model I selected the major factors which affect the rainfall depth through principle component analysis as the model input. Model II adopted characteristic parameter of typhoon, shield height, wind velocity and direction, temperature and atmospheric pressure, and antecedent rainfall of gage station as model input. The results showed that the model II achieved better accuracy than model I. In addition, using 3-hour as simulating time step can provide better accuracy in both rainfall pattern and peak rainfall depth than 1-hour simulation. Therefore, the BPN typhoon rainfall model proposed in this thesis could satisfactorily simulate the pattern and depth of typhoon rainfall.
王奕鈞. "Cadastral Coordinate Transformation Using Artificial Neural Network". Thesis, 2006. http://ndltd.ncl.edu.tw/handle/85629959425775248835.
Pełny tekst źródła國立政治大學
地政研究所
94
Currently, there are two cadastral coordinate systems used in Taiwan. They are TWD67 (Taiwan Datum 1967) and TWD97 (Taiwan Datum 1997) cadastral coordinate systems respectively. Frequently it is necessary to transform from one coordinate system to another. One of the most widely used method is Least-Squares with affine transformations. The artificial neural network (ANN) provides a new technology for cadastral coordinate transformation. The popularity of this methodology is rapidly growing. The greatest advantage of ANN is that it can be used very successfully with a huge quantity of data and free-model estimation that traditional transformation methods cannot be applied. In this research coordinate transformation between TWD67 and TWD97 with artificial neural network (ANN) and Least-Squares with affine transformations were examined. Besides, in order to overcome the so called ‘‘Black Box Problem’’ of ANN, algorithm of applying artificial neural network to develop regional grid-based cadastral coordinate transformation model was proposed. Three data sets with varied sizes from the Taiwan region are used to test the proposed algorithms. The test results show that the coordinate transformation accuracies using the ANN models are better than those of using other methods, such as, Least-Squares with affine transformations. The proposed algorithms and the detailed test results are presented in this paper.