Access the full text.
Sign up today, get DeepDyve free for 14 days.
Jiuxiang Gu, Zhenhua Wang, Jason Kuen, Lianyang Ma, Amir Shahroudy, Bing Shuai, Ting Liu, Xingxing Wang, Gang Wang, Jianfei Cai, Tsuhan Chen (2015)
Recent advances in convolutional neural networksArXiv, abs/1512.07108
J. Bilski, Bartosz Kowalczyk, A. Marjański, M. Gandor, J. Zurada (2021)
A Novel Fast Feedforward Neural Networks Training AlgorithmJournal of Artificial Intelligence and Soft Computing Research, 11
J. Bilski, Bartosz Kowalczyk, A. Marchlewska, J. Zurada (2020)
Local Levenberg-Marquardt Algorithm for Learning Feedforwad Neural NetworksJournal of Artificial Intelligence and Soft Computing Research, 10
Amin Hedayati, Moein Hedayati, M. Esfandyari (2016)
Stock Market Index Prediction Using Artificial Neural NetworkCapital Markets: Asset Pricing & Valuation eJournal
M. Sharif, J. Li, Muhammad Khan, M. Saleem (2020)
Active deep neural network features selection for segmentation and recognition of brain tumors using MRI imagesPattern Recognit. Lett., 129
R. Nowicki, Janusz Starczewski (2017)
A new method for classification of imprecise data using fuzzy rough fuzzificationInf. Sci., 414
Jiyang Dong, K. Lu, Jian Xue, Shuangfeng Dai, Rui Zhai, Weiguo Pan (2018)
Accelerated nonrigid image registration using improved Levenberg-Marquardt methodInf. Sci., 423
Xin Wang, Yi Guo, Yuanyuan Wang, Jinhua Yu (2019)
Automatic breast tumor detection in ABVS images based on convolutional neural network and superpixel patternsNeural Computing and Applications, 31
Y. Mou, Kun Xu (2017)
The media inequality: Comparing the initial human-human and human-AI social interactionsComput. Hum. Behav., 72
Marcin Gabryel, Dawid Lada, Z. Filutowicz, Zofia Patora-Wysocka, Marek Kisiel-Dorohinicki, Guangxing Chen (2022)
Detecting Anomalies in Advertising Web Traffic with the Use of the Variational AutoencoderJournal of Artificial Intelligence and Soft Computing Research, 12
M. Cui, Kai Yang, Xiao-liang Xu, Shengdong Wang, Xiaowei Gao (2016)
A modified Levenberg–Marquardt algorithm for simultaneous estimation of multi-parameters of boundary heat flux by solving transient nonlinear inverse heat conduction problemsInternational Journal of Heat and Mass Transfer, 97
Songqiao Qi, Kaijun Jin, Baisong Li, Yufeng Qian (2020)
The exploration of internet finance by using neural networkJ. Comput. Appl. Math., 369
M. Hagan, M. Menhaj (1994)
Training feedforward networks with the Marquardt algorithmIEEE transactions on neural networks, 5 6
Xin Cai, Yufeng Qian, Qingshan Bai, Wei Liu (2020)
Exploration on the financing risks of enterprise supply chain using Back Propagation neural networkJ. Comput. Appl. Math., 367
Katsuba Yurii, Grigorieva Liudmila (2017)
Application of Artificial Neural Networks in Vehicles’ Design Self-Diagnostic Systems for Safety ReasonsTransportation research procedia, 20
Marcin Zalasiński, Ł. Laskowski, Tacjana Niksa-Rynkiewicz, K. Cpałka, A. Byrski, Krzysztof Przybyszewski, Paweł Trippner, Shiquan Dong (2022)
Evolutionary Algorithm for Selecting Dynamic Signatures Partitioning ApproachJournal of Artificial Intelligence and Soft Computing Research, 12
J. Bilski, Bartosz Kowalczyk, Marek Kisiel-Dorohinicki, A. Siwocha, J. Zurada (2022)
Towards a Very Fast Feedforward Multilayer Neural Networks Training AlgorithmJournal of Artificial Intelligence and Soft Computing Research, 12
AbstractThis paper presents a parallel approach to the Levenberg-Marquardt algorithm (LM). The use of the Levenberg-Marquardt algorithm to train neural networks is associated with significant computational complexity, and thus computation time. As a result, when the neural network has a big number of weights, the algorithm becomes practically ineffective. This article presents a new parallel approach to the computations in Levenberg-Marquardt neural network learning algorithm. The proposed solution is based on vector instructions to effectively reduce the high computational time of this algorithm. The new approach was tested on several examples involving the problems of classification and function approximation, and next it was compared with a classical computational method. The article presents in detail the idea of parallel neural network computations and shows the obtained acceleration for different problems.
Journal of Artificial Intelligence and Soft Computing Research – de Gruyter
Published: Mar 1, 2023
Keywords: feed-forward neural network; neural network learning algorithm; Levenberg-Marquardt algorithm; QR decomposition; Givens rotation
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.