Увійти

Готові списки джерел за темами / Cascade neural networks / Статті в журналах

Статті в журналах з теми "Cascade neural networks"

Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Cascade neural networks.

Автор: Grafiati

Опубліковано: 30 травня 2022

Оновлено: 31 травня 2022

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями

Оберіть тип джерела:

Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Cascade neural networks".

Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.

Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.

Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.

1

Shpinareva, Irina M., Anastasia A. Yakushina, Lyudmila A. Voloshchuk, and Nikolay D. Rudnichenko. "Detection and classification of network attacks using the deep neural network cascade." Herald of Advanced Information Technology 4, no. 3 (October 15, 2021): 244–54. http://dx.doi.org/10.15276/hait.03.2021.4.

Повний текст джерела

Анотація:

This article shows the relevance of developing a cascade of deep neural networks for detecting and classifying network attacks based on an analysis of the practical use of network intrusion detection systems to protect local computer networks. A cascade of deep neural networks consists of two elements. The first network is a hybrid deep neural network that contains convolutional neural network layers and long short-term memory layers to detect attacks. The second network is a CNN convolutional neural network for classifying the most popular classes of network attacks such as Fuzzers, Analysis, Backdoors, DoS, Exploits, Generic, Reconnais-sance, Shellcode, and Worms. At the stage of tuning and training the cascade of deep neural networks, the selection of hyperparame-ters was carried out, which made it possible to improve the quality of the model. Among the available public datasets, one ofthe current UNSW-NB15 datasets was selected, taking into account modern traffic. For the data set under consideration, a data prepro-cessing technology has been developed. The cascade of deep neural networks was trained, tested, and validated on the UNSW-NB15 dataset. The cascade of deep neural networks was tested on real network traffic, which showed its ability to detect and classify at-tacks in a computer network. The use of a cascade of deep neural networks, consisting of a hybrid neural network CNN + LSTM and a neural network CNNhas improved the accuracy of detecting and classifying attacks in computer networks and reduced the fre-quency of false alarms in detecting network attacks

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Pedrycz, W., M. Reformat, and C. W. Han. "Cascade Architectures of Fuzzy Neural Networks." Fuzzy Optimization and Decision Making 3, no. 1 (March 2004): 5–37. http://dx.doi.org/10.1023/b:fodm.0000013070.26870.e6.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Konarev, D. I., and A. A. Gulamov. "Synthesis of Neural Network Architecture for Recognition of Sea-Going Ship Images." Proceedings of the Southwest State University 24, no. 1 (June 23, 2020): 130–43. http://dx.doi.org/10.21869/2223-1560-2020-24-1-130-143.

Повний текст джерела

Анотація:

Purpose of research. The current task is to monitor ships using video surveillance cameras installed along the canal. It is important for information communication support for navigation of the Moscow Canal. The main subtask is direct recognition of ships in an image or video. Implementation of a neural network is perspectively.Methods. Various neural network are described. images of ships are an input data for the network. The learning sample uses CIFAR-10 dataset. The network is built and trained by using Keras and TensorFlow machine learning libraries.Results. Implementation of curving artificial neural networks for problems of image recognition is described. Advantages of such architecture when working with images are also described. The selection of Python language for neural network implementation is justified. The main used libraries of machine learning, such as TensorFlow and Keras are described. An experiment has been conducted to train swirl neural networks with different architectures based on Google collaboratoty service. The effectiveness of different architectures was evaluated as a percentage of correct pattern recognition in the test sample. Conclusions have been drawn about parameters influence of screwing neural network on showing its effectiveness.Conclusion. The network with a single curl layer in each cascade showed insufficient results, so three-stage curls with two and three curl layers in each cascade were used. Feature map extension has the greatest impact on the accuracy of image recognition. The increase in cascades' number has less noticeable effect and the increase in the number of screwdriver layers in each cascade does not always have an increase in the accuracy of the neural network. During the study, a three-frame network with two buckling layers in each cascade and 128 feature maps is defined as an optimal architecture of neural network under described conditions. operability checking of architecture's part under consideration on random images of ships confirmed the correctness of optimal architecture choosing.

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Duan, Shuo, Shuai Xu, Xiao Meng Xu, Xin Zhang, and Chang Li Zhou. "Simultaneous Determination of p-Nitrochlorobenzene and o-Nitrophenol in Mixture by Single-Sweep Oscillopolarography Based on Cascade Neural Network." Advanced Materials Research 217-218 (March 2011): 1469–74. http://dx.doi.org/10.4028/www.scientific.net/amr.217-218.1469.

Повний текст джерела

Анотація:

By combining the improved wavelet neural network and BP neural network, a new structure based on mixed cascade neural network was established. The novel cascade neural network has been used to the oscillopolargriphic signals analysis. By the figure fitting and parameters extracting, we realized the prediction of the simulation samples.The training speed and the predication accuracy can be enhanced by optimizing the network structure and parameters. The result of concentration prediction is satisfied . The method has been applied to the simultaneous determination of p- Nitrochlorobenzene (p-NCB) and o-Nitrophenol (o-NP) in simulation samples with satisfactory results. The Relative error and Recovery of p-NCB、o-NP were 3.76%、96.2%； 4.05%、96.0%, respectively. This novel cascade neural network combines the advantage of wavelet neural networks and BP neural networks, and performs its own functions respectively. It has shown a unique advantage in the overlap peak analyze.

Стилі APA, Harvard, Vancouver, ISO та ін.

5

KWAK, Keun-Chang. "A Development of Cascade Granular Neural Networks." IEICE Transactions on Information and Systems E94-D, no. 7 (2011): 1515–18. http://dx.doi.org/10.1587/transinf.e94.d.1515.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Choi, S., and A. Cichocki. "Cascade neural networks for multichannel blind deconvolution." Electronics Letters 34, no. 12 (1998): 1186. http://dx.doi.org/10.1049/el:19980856.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Smith, H. Allison, and J. Geoffrey Chase. "Identification of Structural System Parameters Using the Cascade-Correlation Neural Network." Journal of Dynamic Systems, Measurement, and Control 116, no. 4 (December 1, 1994): 790–92. http://dx.doi.org/10.1115/1.2899280.

Повний текст джерела

Анотація:

The use of neural networks for structural system identification is receiving an increasing amount of attention through the research focused on structural control and intelligent systems. These systems require continuous monitoring and controlling of structural response; thus, on-line identification techniques are needed to provide real-time information about structural parameters. The Cascade-Correlation (Cascor) neural network is applied here to the structural system identification problem. The Cascor network utilizes a dynamic network architecture and a variable error threshold mechanism which facilitates training and can increase the network’s ability to generalize.

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Patan, Krzysztof. "Local stability conditions for discrete-time cascade locally recurrent neural networks." International Journal of Applied Mathematics and Computer Science 20, no. 1 (March 1, 2010): 23–34. http://dx.doi.org/10.2478/v10006-010-0002-x.

Повний текст джерела

Анотація:

Local stability conditions for discrete-time cascade locally recurrent neural networksThe paper deals with a specific kind of discrete-time recurrent neural network designed with dynamic neuron models. Dynamics are reproduced within each single neuron, hence the network considered is a locally recurrent globally feedforward. A crucial problem with neural networks of the dynamic type is stability as well as stabilization in learning problems. The paper formulates local stability conditions for the analysed class of neural networks using Lyapunov's first method. Moreover, a stabilization problem is defined and solved as a constrained optimization task. In order to tackle this problem, a gradient projection method is adopted. The efficiency and usefulness of the proposed approach are justified by using a number of experiments.

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Shuqi Zhang, Shuqi Zhang. "Cascade Attention-based Spatial-temporal Convolutional Neural Network for Motion Image Posture Recognition." 電腦學刊 33, no. 1 (February 2022): 021–30. http://dx.doi.org/10.53106/199115992022023301003.

Повний текст джерела

Анотація:

<p>The traditional motion posture recognition methods cannot capture the temporal relationship in a video sequence, which leads to the problem that the recognition effect of time-dependent behaviors is not ideal. Therefore, this paper proposes a cascade attention-based spatial-temporal convolutional neural network for motion posture recognition. Firstly, the convolutional neural network is used to model the time sequence relationship in the video, so as to capture the spatial-temporal information in the video efficiently. At the same time, the cascade attention mechanism is used to improve the low learning ability of spatial features caused by channel information moving on the time axis. Meanwhile, a new spatial-temporal network structure is constructed, which includes the spatial-temporal appearance information flow and spatial-temporal motion information flow. Finally, the weighted average method is used to fuse the two spatial-temporal networks to obtain the final recognition result. Experiments are conducted on UCF101 and HMDB51 datasets, respectively, and the recognition accuracy is 96.8% and 79.6%. Experiment results show that compared with the state-of-the-art network methods, the recognition accuracy with the proposed method has better effect and robustness.</p> <p> </p>

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Smit, Mohammad, and Abdel-Nasser Al-Assimi. "Cascade Deep Neural Networks Classifiers for Phonemes Recognition." Journal of Engineering and Applied Sciences 15, no. 7 (March 14, 2020): 1664–70. http://dx.doi.org/10.36478/jeasci.2020.1664.1670.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

11

Jia, Shanshan, Dajun Xing, Zhaofei Yu, and Jian K. Liu. "Dissecting cascade computational components in spiking neural networks." PLOS Computational Biology 17, no. 11 (November 29, 2021): e1009640. http://dx.doi.org/10.1371/journal.pcbi.1009640.

Повний текст джерела

Анотація:

Finding out the physical structure of neuronal circuits that governs neuronal responses is an important goal for brain research. With fast advances for large-scale recording techniques, identification of a neuronal circuit with multiple neurons and stages or layers becomes possible and highly demanding. Although methods for mapping the connection structure of circuits have been greatly developed in recent years, they are mostly limited to simple scenarios of a few neurons in a pairwise fashion; and dissecting dynamical circuits, particularly mapping out a complete functional circuit that converges to a single neuron, is still a challenging question. Here, we show that a recent method, termed spike-triggered non-negative matrix factorization (STNMF), can address these issues. By simulating different scenarios of spiking neural networks with various connections between neurons and stages, we demonstrate that STNMF is a persuasive method to dissect functional connections within a circuit. Using spiking activities recorded at neurons of the output layer, STNMF can obtain a complete circuit consisting of all cascade computational components of presynaptic neurons, as well as their spiking activities. For simulated simple and complex cells of the primary visual cortex, STNMF allows us to dissect the pathway of visual computation. Taken together, these results suggest that STNMF could provide a useful approach for investigating neuronal systems leveraging recorded functional neuronal activity.

Стилі APA, Harvard, Vancouver, ISO та ін.

12

CONG, QIUMEI, WEN YU, and TIANYOU CHAI. "CASCADE PROCESS MODELING WITH MECHANISM-BASED HIERARCHICAL NEURAL NETWORKS." International Journal of Neural Systems 20, no. 01 (February 2010): 1–11. http://dx.doi.org/10.1142/s012906571000219x.

Повний текст джерела

Анотація:

Cascade process, such as wastewater treatment plant, includes many nonlinear sub-systems and many variables. When the number of sub-systems is big, the input-output relation in the first block and the last block cannot represent the whole process. In this paper we use two techniques to overcome the above problem. Firstly we propose a new neural model: hierarchical neural networks to identify the cascade process; then we use serial structural mechanism model based on the physical equations to connect with neural model. A stable learning algorithm and theoretical analysis are given. Finally, this method is used to model a wastewater treatment plant. Real operational data of wastewater treatment plant is applied to illustrate the modeling approach.

Стилі APA, Harvard, Vancouver, ISO та ін.

13

Martinelli, G., F. M. Mascioli, and G. Bei. "Cascade neural network for binary mapping." IEEE Transactions on Neural Networks 4, no. 1 (1993): 148–50. http://dx.doi.org/10.1109/72.182707.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

14

Iyoda, Eduardo Masato, Kaoru Hirota, and Fernando J. Von Zuben. "Sigma-Pi Cascade Extended Hybrid Neural Network." Journal of Advanced Computational Intelligence and Intelligent Informatics 6, no. 3 (October 20, 2002): 126–34. http://dx.doi.org/10.20965/jaciii.2002.p0126.

Повний текст джерела

Анотація:

A nonparametric neural architecture called the Sigma-Pi Cascade extended Hybrid Neural Network σπ-(CHNN) is proposed to extend approximation capabilities in neural architectures such as Projection Pursuit Learning (PPL) and Hybrid Neural Networks (HNN). Like PPL and HNN, σπ-CHNN also uses distinct activation functions in its neurons but, unlike these previous neural architectures, it may consider multiplicative operators in its hidden neurons, enabling it to extract higher-order information from given data. σπ-CHNN uses arbitrary connectivity patterns among neurons. An evolutionary learning algorithm combined with a conjugate gradient algorithm is proposed to automatically design the topology and weights of σπ-CHNN. σπ-CHNN performance is evaluated in five benchmark regression problems. Results show that σπ-CHNN provides competitive performance compared to PPL and HNN in most problems, either in computational requirements to implement the proposed neural architecture or in approximation accuracy. In some problems, σπ-CHNN reduces the approximation error on the order of 10-1 compared to PPL and HNN, whereas in other cases it achieves the same approximation error as these neural architectures but uses a smaller number of hidden neurons (usually 1 hidden neuron less than PPL and HNN).

Стилі APA, Harvard, Vancouver, ISO та ін.

15

Chang, Haonan, Zhuo Xu, and Masayoshi Tomizuka. "Cascade Attribute Network: Decomposing Reinforcement Learning Control Policies using Hierarchical Neural Networks." IFAC-PapersOnLine 53, no. 2 (2020): 8181–86. http://dx.doi.org/10.1016/j.ifacol.2020.12.2317.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

16

Mohamed, Soha Abd El-Moamen, Marghany Hassan Mohamed, and Mohammed F. Farghally. "A New Cascade-Correlation Growing Deep Learning Neural Network Algorithm." Algorithms 14, no. 5 (May 19, 2021): 158. http://dx.doi.org/10.3390/a14050158.

Повний текст джерела

Анотація:

In this paper, a proposed algorithm that dynamically changes the neural network structure is presented. The structure is changed based on some features in the cascade correlation algorithm. Cascade correlation is an important algorithm that is used to solve the actual problem by artificial neural networks as a new architecture and supervised learning algorithm. This process optimizes the architectures of the network which intends to accelerate the learning process and produce better performance in generalization. Many researchers have to date proposed several growing algorithms to optimize the feedforward neural network architectures. The proposed algorithm has been tested on various medical data sets. The results prove that the proposed algorithm is a better method to evaluate the accuracy and flexibility resulting from it.

Стилі APA, Harvard, Vancouver, ISO та ін.

17

Cong, Qiumei, Tianyou Chai, and Wen Yu. "Cascade Process Modeling with Mechanism-Based Hierarchical Neural Networks." IFAC Proceedings Volumes 41, no. 2 (2008): 5563–68. http://dx.doi.org/10.3182/20080706-5-kr-1001.00938.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

18

Habib, Tamer Mekky. "Nonlinear Spacecraft Attitude Control via Cascade-Forward Neural Networks." International Review of Automatic Control (IREACO) 13, no. 3 (May 31, 2020): 146. http://dx.doi.org/10.15866/ireaco.v13i3.19149.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

19

Qiao, Junfei, Fanjun Li, Honggui Han, and Wenjing Li. "Constructive algorithm for fully connected cascade feedforward neural networks." Neurocomputing 182 (March 2016): 154–64. http://dx.doi.org/10.1016/j.neucom.2015.12.003.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

20

Huang, Gao, Shiji Song, and Cheng Wu. "Orthogonal Least Squares Algorithm for Training Cascade Neural Networks." IEEE Transactions on Circuits and Systems I: Regular Papers 59, no. 11 (November 2012): 2629–37. http://dx.doi.org/10.1109/tcsi.2012.2189060.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

21

Wood, M. J., and J. D. Hirst. "Predicting protein secondary structure by cascade-correlation neural networks." Bioinformatics 20, no. 3 (January 22, 2004): 419–20. http://dx.doi.org/10.1093/bioinformatics/btg423.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

22

An, Ye Ji, Kwae Hwan Yoo, Man Gyun Na, and Yeon-Sik Kim. "Critical flow prediction using simplified cascade fuzzy neural networks." Annals of Nuclear Energy 136 (February 2020): 107047. http://dx.doi.org/10.1016/j.anucene.2019.107047.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

23

Dong, Yuan, and Yue Wu. "Adaptive Cascade Deep Convolutional Neural Networks for face alignment." Computer Standards & Interfaces 42 (November 2015): 105–12. http://dx.doi.org/10.1016/j.csi.2015.06.004.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

24

Kharat, J. P. "Comparative Study of Various Neural Network Architectures for MPEG-4 Video Traffic Prediction." International Journal of Advances in Applied Sciences 6, no. 4 (December 1, 2017): 283. http://dx.doi.org/10.11591/ijaas.v6.i4.pp283-292.

Повний текст джерела

Анотація:

<p>Network traffic as it is VBR in nature exhibits strong correlations which make it suitable for prediction. Real-time forecasting of network traffic load accurately and in a computationally efficient manner is the key element of proactive network management and congestion control. This paper comments on the MPEG-4 video traffic predictions evaluated by different types of neural network architectures and compares the performance of the same in terms of mean square error for the same video frames. For that three types of neural architectures are used namely Feed forward, Cascaded Feed forward and Time Delay Neural Network. The results show that cascade feed forward network produces minimum error as compared to other networks. This paper also compares the results of traditional prediction method of averaging of frames for future frame prediction with neural based methods. The experimental results show that nonlinear prediction based on NNs is better suited for traffic prediction purposes than linear forecasting models.</p>

Стилі APA, Harvard, Vancouver, ISO та ін.

25

Du, Xin, Katayoun Farrahi, and Mahesan Niranjan. "Information Bottleneck Theory Based Exploration of Cascade Learning." Entropy 23, no. 10 (October 18, 2021): 1360. http://dx.doi.org/10.3390/e23101360.

Повний текст джерела

Анотація:

In solving challenging pattern recognition problems, deep neural networks have shown excellent performance by forming powerful mappings between inputs and targets, learning representations (features) and making subsequent predictions. A recent tool to help understand how representations are formed is based on observing the dynamics of learning on an information plane using mutual information, linking the input to the representation (I(X;T)) and the representation to the target (I(T;Y)). In this paper, we use an information theoretical approach to understand how Cascade Learning (CL), a method to train deep neural networks layer-by-layer, learns representations, as CL has shown comparable results while saving computation and memory costs. We observe that performance is not linked to information–compression, which differs from observation on End-to-End (E2E) learning. Additionally, CL can inherit information about targets, and gradually specialise extracted features layer-by-layer. We evaluate this effect by proposing an information transition ratio, I(T;Y)/I(X;T), and show that it can serve as a useful heuristic in setting the depth of a neural network that achieves satisfactory accuracy of classification.

Стилі APA, Harvard, Vancouver, ISO та ін.

26

Mahul, Antoine, and Alex Aussem. "Distributed Neural Networks for Quality of Service Estimation in Communication Networks." International Journal of Computational Intelligence and Applications 03, no. 03 (September 2003): 297–308. http://dx.doi.org/10.1142/s1469026803000999.

Повний текст джерела

Анотація:

We study an original scheme based on distributed feedforward neural networks, aimed at modelling several queueing systems in cascade fed with bursty traffic. For each queueing system, a neural network is trained to anticipate the average number of waiting packets, the packet loss rate and the coefficient of variation of the packet inter-departure time, given the mean rate, the peak rate and the coefficient of variation of the packet inter-arrival time. The latter serves for the calculation of the coefficient of variation of the cell inter-arrival time of the aggregated traffic which is fed as input to the next neural network along the path. The potential of this method is successfully illustrated on several single server FIFO (First In, First Out) queues and on small queueing networks made up from a combination of queues in tandem and in parallel fed by a superposition of ideal sources. Our long-term goal is the design of preventive control strategy in a multiservice communication network.

Стилі APA, Harvard, Vancouver, ISO та ін.

27

Vasičkaninová, Anna, Monika Bakošová, and Alajos Mészáros. "Control of heat exchangers in series using neural network predictive controllers." Acta Chimica Slovaca 13, no. 1 (April 1, 2020): 41–48. http://dx.doi.org/10.2478/acs-2020-0007.

Повний текст джерела

Анотація:

AbstractThe paper reveals three applications of neural network predictive control (NNPC) to a system of four heat exchangers (HEs) in series with counterflow configuration to save energy expressed by cooling water in the system of HEs cooling the distillation product. Neural networks (NNs) are used at first in conventional NNPC and subsequently, neural network predictive controllers (NNPCLs) are employed as a master controller in a cascade control, and as a feedback controller in the control system with disturbance measurement. Neural-network-predictive-control-based (NNPC-based) feedback control systems are compared with PI controller based feedback control loop. Series of simulation experiments were done and the results showed that using NNPC-based cascade control reduced cooling water consumption. This control system also significantly reduced the settling time and overshoots in the control responses and provided the best assessed integral quality criteria compared to other control systems. NNPC-based cascade control can also be interesting for industrial use. Generally, simulation results proved that NNPC-based control systems are promising means for the improvement of HEs control and achievement of energy saving.

Стилі APA, Harvard, Vancouver, ISO та ін.

28

Kaveh, M., and R. A. Chayjan. "Mathematical and neural network modelling of terebinth fruit under fluidized bed drying." Research in Agricultural Engineering 61, No. 2 (June 2, 2016): 55–65. http://dx.doi.org/10.17221/56/2013-rae.

Повний текст джерела

Анотація:

The paper presents an application which uses Feed Forward Neural Networks (FFNNs) to model the non-linear behaviour of the terebinth fruit drying. Mathematical models and Artificial Neural Networks (ANNs) were used for prediction of effective moisture diffusivity, specific energy consumption, shrinkage, drying rate and moisture ratio in terebinth fruit. Feed Forward Neural Network (FFBP) and Cascade Forward Neural Network (CFNN) as well as training algorithms of Levenberg-Marquardt (LM) and Bayesian regularization (BR) were used. Air temperature and velocity limits were 40–80°C and 0.81–4.35 m/s, respectively. The best outcome for the use of ANN for the effective moisture diffusivity appertained to CFNN network with BR training algorithm, topology of 2-3-1 and threshold function of TANSIG. Similarly, the best outcome for the use of ANN for drying rate and moisture ratio also appertained to CFNN network with LM training algorithm, topology of 3-2-4-2 and threshold function of TANSIG.

Стилі APA, Harvard, Vancouver, ISO та ін.

29

Benaim, Michel. "On Functional Approximation with Normalized Gaussian Units." Neural Computation 6, no. 2 (March 1994): 319–33. http://dx.doi.org/10.1162/neco.1994.6.2.319.

Повний текст джерела

Анотація:

Feedforward neural networks with a single hidden layer using normalized gaussian units are studied. It is proved that such neural networks are capable of universal approximation in a satisfactory sense. Then, a hybrid learning rule as per Moody and Darken that combines unsupervised learning of hidden units and supervised learning of output units is considered. By using the method of ordinary differential equations for adaptive algorithms (ODE method) it is shown that the asymptotic properties of the learning rule may be studied in terms of an autonomous cascade of dynamical systems. Some recent results from Hirsch about cascades are used to show the asymptotic stability of the learning rule.

Стилі APA, Harvard, Vancouver, ISO та ін.

30

Xu, Yuelei, Mingming Zhu, Shuai Li, Hongxiao Feng, Shiping Ma, and Jun Che. "End-to-End Airport Detection in Remote Sensing Images Combining Cascade Region Proposal Networks and Multi-Threshold Detection Networks." Remote Sensing 10, no. 10 (September 21, 2018): 1516. http://dx.doi.org/10.3390/rs10101516.

Повний текст джерела

Анотація:

Fast and accurate airport detection in remote sensing images is important for many military and civilian applications. However, traditional airport detection methods have low detection rates, high false alarm rates and slow speeds. Due to the power convolutional neural networks in object-detection systems, an end-to-end airport detection method based on convolutional neural networks is proposed in this study. First, based on the common low-level visual features of natural images and airport remote sensing images, region-based convolutional neural networks are chosen to conduct transfer learning for airport images using a limited amount of data. Second, to further improve the detection rate and reduce the false alarm rate, the concepts of “divide and conquer” and “integral loss’’ are introduced to establish cascade region proposal networks and multi-threshold detection networks, respectively. Third, hard example mining is used to improve the object discrimination ability and the training efficiency of the network during sample training. Additionally, a cross-optimization strategy is employed to achieve convolution layer sharing between the cascade region proposal networks and the subsequent multi-threshold detection networks, and this approach significantly decreases the detection time. The results show that the method established in this study can accurately detect various types of airports in complex backgrounds with a higher detection rate, lower false alarm rate, and shorter detection time than existing airport detection methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

31

Cai, Chunsheng, and Peter de B. Harrington. "Wavelet Transform Preprocessing for Temperature Constrained Cascade Correlation Neural Networks." Journal of Chemical Information and Computer Sciences 39, no. 5 (September 9, 1999): 874–80. http://dx.doi.org/10.1021/ci9903253.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

32

Shaaban, Khaled M., and Robert J. Schalkoff. "Synthesis of cascade recurrent neural networks using feedforward generalization properties." Information Sciences 108, no. 1-4 (July 1998): 207–17. http://dx.doi.org/10.1016/s0020-0255(97)10060-3.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

33

Tang, Yi, Wenbin Zou, Zhi Jin, Yuhuan Chen, Yang Hua, and Xia Li. "Weakly Supervised Salient Object Detection With Spatiotemporal Cascade Neural Networks." IEEE Transactions on Circuits and Systems for Video Technology 29, no. 7 (July 2019): 1973–84. http://dx.doi.org/10.1109/tcsvt.2018.2859773.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

34

Huang, Zhenhua, Zhenyu Wang, and Rui Zhang. "Cascade2vec: Learning Dynamic Cascade Representation by Recurrent Graph Neural Networks." IEEE Access 7 (2019): 144800–144812. http://dx.doi.org/10.1109/access.2019.2942853.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

35

Negri, Gabriel, Filipe Nazário, José Oliveira, and Ademir Nied. "Back-emf Based Rotor Position Estimation For Low Cost Pmsm Drive Using Fully Connected Cascade Artificial Neural Networks." Eletrônica de Potência 23, no. 1 (March 1, 2018): 69–77. http://dx.doi.org/10.18618/rep.2018.1.2728.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

36

Aribowo, Widi. "Slime Mould Algorithm Training Neural Network in Automatic Voltage Regulator." Trends in Sciences 19, no. 3 (January 20, 2022): 2145. http://dx.doi.org/10.48048/tis.2022.2145.

Повний текст джерела

Анотація:

The research is proposed a new method of artificial intelligence (AI) to control automatic voltage regulators. A neural network has improved using a metaheuristic method, namely the slime mould algorithm (SMA). SMA has an algorithm based on the mode of slime mold in nature. SMA has characteristics that use adaptive weights to simulate the process to generate feedback from the movement of bio-oscillator-based slime molds in foraging, exploring, and exploiting areas. The performance of the proposed method is focused on speed and rotor angle. To know the competence and potency of the proposed method, a comparison with feed-forward backpropagation neural networks (FFBNN), cascade-forward backpropagation neural networks (CFBNN), Elman-recurrent neural networks (E-RNN), focused time delay neural network (FTDNN), and Distributed Time Delay Neural Network (DTDNN) method are applied. It can be concluded that the proposed method has the best ability. The Proposed method has ability to reduce the overshoot speed with an average value of 0.78 % and the overshoot rotor angle with an average value of 2.134 %.

Стилі APA, Harvard, Vancouver, ISO та ін.

37

Golpour, Iman, Ana Cristina Ferrão, Fernando Gonçalves, Paula M. R. Correia, Ana M. Blanco-Marigorta, and Raquel P. F. Guiné. "Extraction of Phenolic Compounds with Antioxidant Activity from Strawberries: Modelling with Artificial Neural Networks (ANNs)." Foods 10, no. 9 (September 20, 2021): 2228. http://dx.doi.org/10.3390/foods10092228.

Повний текст джерела

Анотація:

This research study focuses on the evaluation of the total phenolic compounds (TPC) and antioxidant activity (AOA) of strawberries according to different experimental extraction conditions by applying the Artificial Neural Networks (ANNs) technique. The experimental data were applied to train ANNs using feed- and cascade-forward backpropagation models with Levenberg-Marquardt (LM) and Bayesian Regulation (BR) algorithms. Three independent variables (solvent concentration, volume/mass ratio and extraction time) were used as ANN inputs, whereas the three variables of total phenolic compounds, DPPH and ABTS antioxidant activities were considered as ANN outputs. The results demonstrate that the best cascade- and feed-forward backpropagation topologies of ANNs for the prediction of total phenolic compounds and DPPH and ABTS antioxidant activity factors were the 3-9-1, 3-4-4-1 and 3-13-10-1 structures, with the training algorithms of trainlm, trainbr, trainlm and threshold functions of tansig-purelin, tansig-tansig-tansig and purelin-tansig-tansig, respectively. The best R2 values for the predication of total phenolic compounds and DPPH and ABTS antioxidant activity factors were 0.9806 (MSE = 0.0047), 0.9651 (MSE = 0.0035) and 0.9756 (MSE = 0.00286), respectively. According to the comparison of ANNs, the results showed that the cascade-forward backpropagation network showed better performance than the feed-forward backpropagation network for predicting the TPC, and the FFBP network, in predicting the DPPH and ABTS antioxidant activity factors, had more precision than the cascade-forward backpropagation network. The ANN technique is a potential method for estimating targeted total phenolic compounds and the antioxidant activity of strawberries.

Стилі APA, Harvard, Vancouver, ISO та ін.

38

Yan, Shaohong, Hailong Zhao, Liangxu Liu, Qiaozhi Sang, Peng Chen, and Jie Li. "Application Study of Sigmoid Regularization Method in Coke Quality Prediction." Complexity 2020 (July 20, 2020): 1–10. http://dx.doi.org/10.1155/2020/8785047.

Повний текст джерела

Анотація:

Coke is an indispensable and vital flue for blast furnace smelting, during which it plays a key role as a reducing agent, heat source, and support skeleton. Models of prediction of coke quality based on ANN are established to map the functional relationship between quality parameters Mt, Ad, Vdaf, St,d, and caking property (X, Y, and G) of mixed coal and quality parameters Ad, St,d, coke reactivity index (CRI), and coke strength after reaction (CSR) of coke. A regularized network training method based on Sigmoid function is designed considering that redundancy of network structure may lead to the learning of undesired noise, in which weights having little impact on performance and leading to overfitting are removed in terms of computational complexity and training errors. The cascade forward neural network with validation is found to be the most suitable one for coke quality prediction, with errors around 5%, followed by feedforward neural network structure and radial basis neural networks. The cascade forward neural network may play a guiding role during the coke production.

Стилі APA, Harvard, Vancouver, ISO та ін.

39

Jahagirdar, Aditi, and Rashmi Phalnikar. "Comparison of feed forward and cascade forward neural networks for human action recognition." Indonesian Journal of Electrical Engineering and Computer Science 25, no. 2 (February 1, 2022): 892. http://dx.doi.org/10.11591/ijeecs.v25.i2.pp892-899.

Повний текст джерела

Анотація:

Humans can perform an enormous number of actions like running, walking, pushing, and punching, and can perform them in multiple ways. Hence recognizing a human action from a video is a challenging task. In a supervised learning environment, actions are first represented using robust features and then a classifier is trained for classification. The selection of a classifier does affect the performance of human action recognition. This work focuses on the comparison of two structures of the neural network, namely, feed forward neural network and cascade forward neural network, for human action recognition. Histogram of oriented gradients (HOG) and histogram of optical flow (HOF) are used as features for representing the actions. HOG represents the spatial features of the video while HOF gives motion features of the video. The performance of two neural network architectures is compared based on recognition accuracy. Well-known publically available datasets for action and interaction detection are used for testing. It is seen that, for human action recognition applications, feed forward neural network gives better results in terms of higher recognition accuracy than Cascade forward neural network.

Стилі APA, Harvard, Vancouver, ISO та ін.

40

Rao, Jinjun, Bo Li, Zhen Zhang, Dongdong Chen, and Wojciech Giernacki. "Position Control of Quadrotor UAV Based on Cascade Fuzzy Neural Network." Energies 15, no. 5 (February 26, 2022): 1763. http://dx.doi.org/10.3390/en15051763.

Повний текст джерела

Анотація:

In this article, a cascade fuzzy neural network (FNN) control approach is proposed for position control of quadrotor unmanned aerial vehicle (UAV) system with high coupling and underactuated. For the attitude loop with limited range, the FNN controller parameters were trained offline using flight data, whereas for the position loop, the method based on FNN compensation proportional-integral-derivative (PID) was adopted to tune the system online adaptively. This method not only combined the advantages of fuzzy systems and neural networks but also reduced the amount of calculation for cascade neural network control. Simulations of fixed set point flight and spiral and square trajectory tracking flight were then conducted. The comparison of the results showed that our method had advantages in terms of minimizing overshoot and settling time. Finally, flight experiments were carried out on a DJI Tello quadrotor UAV. The experimental results showed that the proposed controller had good performance in position control.

Стилі APA, Harvard, Vancouver, ISO та ін.

41

Liu, Hanqing, Xiaojun Li, Jin Wei, and Xiaodong Kang. "Cerebral Arterial Stenosis Detection Based on a Retained Two-Stage Detection Algorithm." Discrete Dynamics in Nature and Society 2022 (April 26, 2022): 1–12. http://dx.doi.org/10.1155/2022/4494411.

Повний текст джерела

Анотація:

Stroke is one of the fatal diseases worldwide, and its primary mechanism is produced by cerebrovascular stenosis, blockages, or embolisms. Computer-aided diagnosis can assist clinical practitioners in identifying cerebrovascular anomalies, elucidating the precise lesions’ location in the patients, and providing guidance for clinical therapy. Due to different portions of the cerebrovascular possessing diverse morphological properties and the limited narrow area, the detection effect is unsatisfactory. A retrained two-stage algorithm for detecting cerebral arterial stenosis in CTA images is proposed to solve these problems by further fusing image features and improving the quality of regions of interest. In Faster R-CNN and Libra R-CNN, the backbone network was Resnet50, with deformable convolutional and nonlocal neural networks introduced in the third, fourth, and fifth stages of the backbone network. Deformable convolutional networks learned offsets to extract morphological features of blood vessels in different tomographic planes. Nonlocal neural networks fused global information and extracted global features from location information of feature maps. A cascade detector refined object classification and bounding box regression before prediction. The experimental results show that the retained algorithm increases mAP by 7.3% and 7.5%, respectively, compared with Faster R-CNN and Libra R-CNN. Deformable convolutional networks, nonlocal neural networks, and cascade detectors are incorporated into further feature fusion; thus, semantic information about the cerebrovascular structure is learned, demonstrating more accurate stenotic region detection and demonstrating generalizability across different two-stage algorithms.

Стилі APA, Harvard, Vancouver, ISO та ін.

42

Liu, Hanqing, Xiaojun Li, Jin Wei, and Xiaodong Kang. "Cerebral Arterial Stenosis Detection Based on a Retained Two-Stage Detection Algorithm." Discrete Dynamics in Nature and Society 2022 (April 26, 2022): 1–12. http://dx.doi.org/10.1155/2022/4494411.

Повний текст джерела

Анотація:

Stroke is one of the fatal diseases worldwide, and its primary mechanism is produced by cerebrovascular stenosis, blockages, or embolisms. Computer-aided diagnosis can assist clinical practitioners in identifying cerebrovascular anomalies, elucidating the precise lesions’ location in the patients, and providing guidance for clinical therapy. Due to different portions of the cerebrovascular possessing diverse morphological properties and the limited narrow area, the detection effect is unsatisfactory. A retrained two-stage algorithm for detecting cerebral arterial stenosis in CTA images is proposed to solve these problems by further fusing image features and improving the quality of regions of interest. In Faster R-CNN and Libra R-CNN, the backbone network was Resnet50, with deformable convolutional and nonlocal neural networks introduced in the third, fourth, and fifth stages of the backbone network. Deformable convolutional networks learned offsets to extract morphological features of blood vessels in different tomographic planes. Nonlocal neural networks fused global information and extracted global features from location information of feature maps. A cascade detector refined object classification and bounding box regression before prediction. The experimental results show that the retained algorithm increases mAP by 7.3% and 7.5%, respectively, compared with Faster R-CNN and Libra R-CNN. Deformable convolutional networks, nonlocal neural networks, and cascade detectors are incorporated into further feature fusion; thus, semantic information about the cerebrovascular structure is learned, demonstrating more accurate stenotic region detection and demonstrating generalizability across different two-stage algorithms.

Стилі APA, Harvard, Vancouver, ISO та ін.

43

Gervini, Vitor Irigon, and Eduardo André Perondi. "Cascade Control of a Pneumatic Servo Positioning System Using Neural Networks." Advanced Materials Research 902 (February 2014): 225–30. http://dx.doi.org/10.4028/www.scientific.net/amr.902.225.

Повний текст джерела

Анотація:

This paper deals with the nonlinear control of pneumatic servo positioners. It is proposed the use of a neural network technique associated with a nonlinear cascade control strategy, as a means of bypassing strong difficulties common to the practical implementation of model based strategies in pneumatic systems control. Such difficulties are associated to the precise plant identification that, in the case of pneumatic servo positioners, is usually very complex and hard to find. The experimental results of position tracking control presented in the paper allow us to conclude that the neural network technique applied in this work can avoid the need of execution of time expensive experiments usually required to perform precise identification of the plant characteristics used in model based control strategies for pneumatic servo positioners.

Стилі APA, Harvard, Vancouver, ISO та ін.

44

Velusamy, K., and R. Amalraj. "Prediction of the Stock Price Using Fuzzy Cascade Correlation Neural Networks." International Journal of Computer Sciences and Engineering 7, no. 5 (May 31, 2019): 81–85. http://dx.doi.org/10.26438/ijcse/v7i5.8185.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

45

Saeed, Anwar, Ayoub Al-Hamadi, and Heiko Neumann. "Facial point localization via neural networks in a cascade regression framework." Multimedia Tools and Applications 77, no. 2 (January 31, 2017): 2261–83. http://dx.doi.org/10.1007/s11042-016-4261-x.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

46

Hoang, Van-Thanh, and Kang-Hyun Jo. "3-D Human Pose Estimation Using Cascade of Multiple Neural Networks." IEEE Transactions on Industrial Informatics 15, no. 4 (April 2019): 2064–72. http://dx.doi.org/10.1109/tii.2018.2864824.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

47

Wong, B. K., T. A. Bodnovich, and V. S.-K. Lai. "The use of cascade-correlation neural networks in University fund raising." Journal of the Operational Research Society 51, no. 8 (August 2000): 913–20. http://dx.doi.org/10.1057/palgrave.jors.2600996.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

48

Shaban, K., A. El-Hag, and A. Matveev. "A cascade of artificial neural networks to predict transformers oil parameters." IEEE Transactions on Dielectrics and Electrical Insulation 16, no. 2 (April 2009): 516–23. http://dx.doi.org/10.1109/tdei.2009.4815187.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

49

Wong, B. K., T. A. Bodnovich, and V. S. K. Lai. "The Use of Cascade-Correlation Neural Networks in University Fund Raising." Journal of the Operational Research Society 51, no. 8 (August 2000): 913. http://dx.doi.org/10.2307/254047.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

50

Heidari, Alireza, Vassilios G. Agelidis, Josep Pou, Jamshid Aghaei, and Amer M. Y. M. Ghias. "Reliability Worth Analysis of Distribution Systems Using Cascade Correlation Neural Networks." IEEE Transactions on Power Systems 33, no. 1 (January 2018): 412–20. http://dx.doi.org/10.1109/tpwrs.2017.2705185.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Ми пропонуємо знижки на всі преміум-плани для авторів, чиї праці увійшли до тематичних добірок літератури. Зв'яжіться з нами, щоб отримати унікальний промокод!