Bibliografias temáticas / Two-layers neural networks

Índice

Artigos de revistas
Teses / dissertações
Capítulos de livros
Trabalhos de conferências
Relatórios de organizações

Literatura científica selecionada sobre o tema "Two-layers neural networks"

Autor: Grafiati

Publicado: 19 de abril de 2025

Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos

Selecione um tipo de fonte:

Consulte a lista de atuais artigos, livros, teses, anais de congressos e outras fontes científicas relevantes para o tema "Two-layers neural networks".

Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.

Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.

Artigos de revistas sobre o assunto "Two-layers neural networks"

Wei, Chih-Chiang. "Comparison of River Basin Water Level Forecasting Methods: Sequential Neural Networks and Multiple-Input Functional Neural Networks". Remote Sensing 12, n.º 24 (20 de dezembro de 2020): 4172. http://dx.doi.org/10.3390/rs12244172.

Texto completo da fonte

Resumo:

To precisely forecast downstream water levels in catchment areas during typhoons, the deep learning artificial neural networks were employed to establish two water level forecasting models using sequential neural networks (SNNs) and multiple-input functional neural networks (MIFNNs). SNNs, which have a typical neural network structure, are network models constructed using sequential methods. To develop a network model capable of flexibly consolidating data, MIFNNs are employed for processing data from multiple sources or with multiple dimensions. Specifically, when images (e.g., radar reflectivity images) are used as input attributes, feature extraction is required to provide effective feature maps for model training. Therefore, convolutional layers and pooling layers were adopted to extract features. Long short-term memory (LSTM) layers adopted during model training enabled memory cell units to automatically determine the memory length, providing more useful information. The Hsintien River basin in northern Taiwan was selected as the research area and collected relevant data from 2011 to 2019. The input attributes comprised one-dimensional data (e.g., water levels at river stations, rain rates at rain gauges, and reservoir release) and two-dimensional data (i.e., radar reflectivity mosaics). Typhoons Saola, Soudelor, Dujuan, and Megi were selected, and the water levels 1 to 6 h after the typhoons struck were forecasted. The results indicated that compared with linear regressions (REG), SNN using dense layers (SNN-Dense), and SNN using LSTM layers (SNN-LSTM) models, superior forecasting results were achieved for the MIFNN model. Thus, the MIFNN model, as the optimal model for water level forecasting, was identified.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Yin, Chun Hua, Jia Wei Chen e Lei Chen. "Weight to Vision Neural Network Information Processing Influence Research". Advanced Materials Research 605-607 (dezembro de 2012): 2131–36. http://dx.doi.org/10.4028/www.scientific.net/amr.605-607.2131.

Texto completo da fonte

Resumo:

Many factors influence vision neural network information processing process, for example: Signal initial value, weight, time and number of learning. This paper discussed the importance of weight in vision neural network information processing process. Different weight values can cause different results in neural networks learning. We structure a vision neural network model with three layers based on synapse dynamics at first. Then we change the weights of the vision neural network model’s to make the three layers a neural network of learning Chinese characters. At last we change the initial weight distribution to simulate the neural network of process of the learning Chinese words. Two results are produced. One is that weight plays a very important role in vision neural networks learning, the other is that different initial weight distributions have different results in vision neural networks learning.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Carpenter, William C., e Margery E. Hoffman. "Guidelines for the selection of network architecture". Artificial Intelligence for Engineering Design, Analysis and Manufacturing 11, n.º 5 (novembro de 1997): 395–408. http://dx.doi.org/10.1017/s0890060400003322.

Texto completo da fonte

Resumo:

AbstractThis paper is concerned with presenting guidelines to aide in the selection of the appropriate network architecture for back-propagation neural networks used as approximators. In particular, its goal is to indicate under what circumstances neural networks should have two hidden layers and under what circumstances they should have one hidden layer. Networks with one and with two hidden layers were used to approximate numerous test functions. Guidelines were developed from the results of these investigations.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Baptista, Marcia, Helmut Prendinger e Elsa Henriques. "Prognostics in Aeronautics with Deep Recurrent Neural Networks". PHM Society European Conference 5, n.º 1 (22 de julho de 2020): 11. http://dx.doi.org/10.36001/phme.2020.v5i1.1230.

Texto completo da fonte

Resumo:

Recurrent neural networks (RNNs) such as LSTM and GRU are not new to the field of prognostics. However, the performance of neural networks strongly depends on their architectural structure. In this work, we investigate a hybrid network architecture that is a combination of recurrent and feed-forward (conditional) layers. Two networks, one recurrent and another feed-forward, are chained together, with inference and weight gradients being learned using the standard back-propagation learning procedure. To better tune the network, instead of using raw sensor data, we do some preprocessing on the data, using mostly simple but effective statistics (researched in previous work). This helps the feature extraction phase and eases the problem of finding a suitable network configuration among the immense set of possible ones. This is not the first proposal of a hybrid network in prognostics but our work is novel in the sense that it performs a more comprehensive comparison of this type of architecture for different RNN layers and number of layers. Also, we compare our work with other classical machine learning methods. Evaluation is performed on two real-world case studies from the aero-engine industry: one involving a critical valve subsystem of the jet engine and another the whole reliability of the jet engine. Our goal here is to compare two cases contrasting micro (valve) and macro (whole engine) prognostics. Our results indicate that the performance of the LSTM and GRU deep networks are significantly better than that of other models.

Estilos ABNT, Harvard, Vancouver, APA, etc.

PAUGAM-MOISY, HÉLÈNE. "HOW TO MAKE GOOD USE OF MULTILAYER NEURAL NETWORKS". Journal of Biological Systems 03, n.º 04 (dezembro de 1995): 1177–91. http://dx.doi.org/10.1142/s0218339095001064.

Texto completo da fonte

Resumo:

This article is a survey of recent advances on multilayer neural networks. The first section is a short summary on multilayer neural networks, their history, their architecture and their learning rule, the well-known back-propagation. In the following section, several theorems are cited, which present one-hidden-layer neural networks as universal approximators. The next section points out that two hidden layers are often required for exactly realizing d-dimensional dichotomies. Defining the frontier between one-hidden-layer and two-hidden-layer networks is still an open problem. Several bounds on the size of a multilayer network which learns from examples are presented and we enhance the fact that, even if all can be done with only one hidden layer, more often, things can be done better with two or more hidden layers. Finally, this assertion 'is supported by the behaviour of multilayer neural networks in two applications: prediction of pollution and odor recognition modelling.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Vetrov, Igor A., e Vladislav V. Podtopelny. "Features of building neural networks taking into account the specifics of their training to solve the tasks of searching for network attacks". Proceedings of Tomsk State University of Control Systems and Radioelectronics 26, n.º 2 (2023): 42–50. http://dx.doi.org/10.21293/1818-0442-2023-26-2-42-50.

Texto completo da fonte

Resumo:

The problems of building neural networks to solve the problems of detecting network intrusions, taking into account modern publicly available technologies, are considered. Several configurations of neural networks are analyzed: a simple perceptron, a combined network consisting of two interconnected networks, simplified networks based on a simple perceptron, LSTM networks using hidden layers with data compression function. The weaknesses and strengths of neural network architectures are considered, taking into account the specifics of their training based on abnormal traffic datasets in intrusion detection tasks.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Petzka, Henning, Martin Trimmel e Cristian Sminchisescu. "Notes on the Symmetries of 2-Layer ReLU-Networks". Proceedings of the Northern Lights Deep Learning Workshop 1 (6 de fevereiro de 2020): 6. http://dx.doi.org/10.7557/18.5150.

Texto completo da fonte

Resumo:

Symmetries in neural networks allow different weight configurations leading to the same network function. For odd activation functions, the set of transformations mapping between such configurations have been studied extensively, but less is known for neural networks with ReLU activation functions. We give a complete characterization for fully-connected networks with two layers. Apart from two well-known transformations, only degenerated situations allow additional transformations that leave the network function unchanged. Reduction steps can remove only part of the degenerated cases. Finally, we present a non-degenerate situation for deep neural networks leading to new transformations leaving the network function intact.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Lamy, Lucas, e Paulo Henrique Siqueira. "The Null Layer: increasing convolutional neural network efficiency". Caderno Pedagógico 22, n.º 6 (4 de abril de 2025): e15344. https://doi.org/10.54033/cadpedv22n6-050.

Texto completo da fonte

Resumo:

Convolutional neural networks are currently used in many applications; however, their construction involves a sequence of choices that can drastically affect the final network accuracy. In addition to the choice of architecture and hyperparameters, weight initialization of the layers is an essential step. We analyzed two different initialization methods in the layers to study their impact on network accuracy. The proposed method, the Null Layer, has a weight initialization of the first convolutional layer equal to zero, whereas the other layers have another type of initialization. The second method, the traditional method, uses the same weight initialization for all layers. Three different networks, four datasets, five activation functions, and three weight initializations were used for the tests. The results showed that the Null Layer method is an efficient approach for increasing network accuracy. It presented better accuracy in 53% of the tests than the traditional method without additional computational cost.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Shpinareva, Irina M., Anastasia A. Yakushina, Lyudmila A. Voloshchuk e Nikolay D. Rudnichenko. "Detection and classification of network attacks using the deep neural network cascade". Herald of Advanced Information Technology 4, n.º 3 (15 de outubro de 2021): 244–54. http://dx.doi.org/10.15276/hait.03.2021.4.

Texto completo da fonte

Resumo:

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

Estilos ABNT, Harvard, Vancouver, APA, etc.

Chen, Jingfeng. "Spam mail classification using back propagation neural networks". Applied and Computational Engineering 5, n.º 1 (14 de junho de 2023): 438–49. http://dx.doi.org/10.54254/2755-2721/5/20230617.

Texto completo da fonte

Resumo:

Mail classification methods based on machine learning have been introduced to combat spams. However, few researches focus on the most powerful machine learning model that is neural networks. In this paper, the author trains BP neural networks to detect spams. The inputs of the neural networks are only information about words, punctures, signs, numbers and illegal words. Five neural networks which are different in number of neurons and number of layers are experimented on. All networks apply Rectified Linear Unit (ReLU) functions and Momentum learning technology. The results show that the network with four hidden layers enjoys the best classifying accuracy of 97.0%. In networks with two hidden layers, when the number of neurons in each layer is above 300, the accuracy is between 95.5% and 96.0%; and 100 neurons in each layer result in an accuracy of 93.8%. Although the training only captures information of words, punctures and signs, the networks have achieved high accuracy, and the author suggests that making the computer understand sentences as well as other kinds of improvements can lead to even higher performance.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Mais fontes

Teses / dissertações sobre o assunto "Two-layers neural networks"

Dabo, Issa-Mbenard. "Applications de la théorie des matrices aléatoires en grandes dimensions et des probabilités libres en apprentissage statistique par réseaux de neurones". Electronic Thesis or Diss., Bordeaux, 2025. http://www.theses.fr/2025BORD0021.

Texto completo da fonte

Resumo:

Le fonctionnement des algorithmes d’apprentissage automatique repose grandement sur la structure des données qu’ils doivent utiliser. La majorité des travaux de recherche en apprentissage automatique se concentre sur l’étude de données homogènes, souvent modélisées par des variables aléatoires indépendantes et identiquement distribuées. Pourtant, les données apparaissant en pratique sont souvent hétérogènes. Nous proposons dans cette thèse de considérer des données hétérogènes en les dotant d’un profil de variance. Cette notion, issue de la théorie des matrices aléatoires, nous permet notamment d’étudier des données issues de modèles de mélanges. Nous nous intéressons plus particulièrement à la problématique de la régression ridge à travers deux modèles : la régression ridge linéaire (linear ridge model) et la régression ridge à caractéristiques aléatoires (random feature ridge model). Nous étudions dans cette thèse la performance de ces deux modèles dans le cadre de la grande dimension, c’est-à-dire lorsque la taille de l’échantillon d’entraînement et la dimension des données tendent vers l’infini avec des vitesses comparables. Dans cet objectif, nous proposons des équivalents asymptotiques de l’erreur d’entraînement et de l’erreur de test relatives aux modèles d’intérêt. L’obtention de ces équivalents repose grandement sur l’étude spectrale issue de la théorie des matrices aléatoires, des probabilités libres et de la théorie des trafics. En effet, la mesure de la performance de nombreux modèles d’apprentissage dépend de la distribution des valeurs propres de matrices aléatoires. De plus, ces résultats nous ont permis d’observer des phénomènes spécifiques à la grande dimension, comme le phénomène de la double descente. Notre étude théorique s’accompagne d’expériences numériques illustrant la précision des équivalents asymptotiques que nous fournissons
The functioning of machine learning algorithms relies heavily on the structure of the data they are given to study. Most research work in machine learning focuses on the study of homogeneous data, often modeled by independent and identically distributed random variables. However, data encountered in practice are often heterogeneous. In this thesis, we propose to consider heterogeneous data by endowing them with a variance profile. This notion, derived from random matrix theory, allows us in particular to study data arising from mixture models. We are particularly interested in the problem of ridge regression through two models: the linear ridge model and the random feature ridge model. In this thesis, we study the performance of these two models in the high-dimensional regime, i.e., when the size of the training sample and the dimension of the data tend to infinity at comparable rates. To this end, we propose asymptotic equivalents for the training error and the test error associated with the models of interest. The derivation of these equivalents relies heavily on spectral analysis from random matrix theory, free probability theory, and traffic theory. Indeed, the performance measurement of many learning models depends on the distribution of the eigenvalues of random matrices. Moreover, these results enabled us to observe phenomena specific to the high-dimensional regime, such as the double descent phenomenon. Our theoretical study is accompanied by numerical experiments illustrating the accuracy of the asymptotic equivalents we provide

Estilos ABNT, Harvard, Vancouver, APA, etc.

Cheng, Wei-Hua, e 鄭維華. "Web Log Analysis Using Two Layers Neural Network". Thesis, 2003. http://ndltd.ncl.edu.tw/handle/05737061743395410229.

Texto completo da fonte

Resumo:

碩士
國立臺灣科技大學
電機工程系
91
With the rapidly developing internet, all kinds of applications based on it, like E-Commerce or academic communication, have become more and more essential for the modern people. These applications are all based on the secure network environment. So Network Security has become the hottest research topic currently and its importance grows rapidly for each day. This thesis proposes a Web log analysis system based on Neural Network, using advantage of learning automatically to improve the reliability. With two layers of Neural Network, we can resolve the category to which the attack belongs and even detect the new category attack never found before. The core of the Web log analysis system is to utilize the leaning feature of Neural Network to cope with swiftly changing attacks and to protect the security of all kinds of network applications.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Capítulos de livros sobre o assunto "Two-layers neural networks"

Thomas, Alan J., Miltos Petridis, Simon D. Walters, Saeed Malekshahi Gheytassi e Robert E. Morgan. "Two Hidden Layers are Usually Better than One". In Engineering Applications of Neural Networks, 279–90. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-65172-9_24.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Furusho, Yasutaka, Tongliang Liu e Kazushi Ikeda. "Skipping Two Layers in ResNet Makes the Generalization Gap Smaller than Skipping One or No Layer". In Proceedings of the International Neural Networks Society, 349–58. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-16841-4_36.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Zhang, Jiantao, e Pingjian Zhang. "Deep Recurrent Neural Networks with Nonlinear Masking Layers and Two-Level Estimation for Speech Separation". In Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series, 397–411. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-30490-4_32.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Mikriukov, Georgii, Gesina Schwalbe, Christian Hellert e Korinna Bade. "Revealing Similar Semantics Inside CNNs: An Interpretable Concept-Based Comparison of Feature Spaces". In Communications in Computer and Information Science, 3–20. Cham: Springer Nature Switzerland, 2025. https://doi.org/10.1007/978-3-031-74630-7_1.

Texto completo da fonte

Resumo:

Abstract Safety-critical applications require transparency in artificial intelligence (AI) components, but widely used convolutional neural networks (CNNs) widely used for perception tasks lack inherent interpretability. Hence, insights into what CNNs have learned are primarily based on performance metrics, because these allow, e.g., for cross-architecture CNN comparison. However, these neglect how knowledge is stored inside. To tackle this yet unsolved problem, our work proposes two methods for estimating the layer-wise similarity between semantic information inside CNN latent spaces. These allow insights into both the flow and likeness of semantic information within CNN layers, and into the degree of their similarity between different network architectures. As a basis, we use two renowned explainable artificial intelligence (XAI) techniques, which are used to obtain concept activation vectors, i.e., global vector representations in the latent space. These are compared with respect to their activation on test inputs. When applied to three diverse object detectors and two datasets, our methods reveal that (1) similar semantic concepts are learned regardless of the CNN architecture, and (2) similar concepts emerge in similar relative layer depth, independent of the total number of layers. Finally, our approach poses a promising step towards semantic model comparability and comprehension of how different CNNs process semantic information.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Huang, Lixing, Jietao Diao, Shuhua Teng, Zhiwei Li, Wei Wang, Sen Liu, Minghou Li e Haijun Liu. "A Method for Obtaining Highly Robust Memristor Based Binarized Convolutional Neural Network". In Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications, 813–22. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-2456-9_82.

Texto completo da fonte

Resumo:

AbstractRecently, memristor based binarized convolutional neural network has been widely investigated owing to its strong processing capability, low power consumption and high computing efficiency.However, it has not been widely applied in the field of embedded neuromorphic computing for manufacturing technology of the memristor being not mature. With respect to this, we propose a method for obtaining highly robust memristor based binarized convolutional neural network. To demonstrate the performance of the method, a convolutional neural network architecture with two layers is used for simulation, and the simulation results show that binarized convolutional neural network can still achieve more than 96.75% recognition rate on MNIST dataset under the condition of 80% yield of the memristor array, and the recognition rate is 94.53% when the variation of memristance is 26%, and it is 94.66% when the variation of the neuron output is 0.8.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Mikriukov, Georgii, Gesina Schwalbe, Christian Hellert e Korinna Bade. "Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability". In Communications in Computer and Information Science, 499–524. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-44067-0_26.

Texto completo da fonte

Resumo:

AbstractAnalysis of how semantic concepts are represented within Convolutional Neural Networks (CNNs) is a widely used approach in Explainable Artificial Intelligence (XAI) for interpreting CNNs. A motivation is the need for transparency in safety-critical AI-based systems, as mandated in various domains like automated driving. However, to use the concept representations for safety-relevant purposes, like inspection or error retrieval, these must be of high quality and, in particular, stable. This paper focuses on two stability goals when working with concept representations in computer vision CNNs: stability of concept retrieval and of concept attribution. The guiding use-case is a post-hoc explainability framework for object detection (OD) CNNs, towards which existing concept analysis (CA) methods are successfully adapted. To address concept retrieval stability, we propose a novel metric that considers both concept separation and consistency, and is agnostic to layer and concept representation dimensionality. We then investigate impacts of concept abstraction level, number of concept training samples, CNN size, and concept representation dimensionality on stability. For concept attribution stability we explore the effect of gradient instability on gradient-based explainability methods. The results on various CNNs for classification and object detection yield the main findings that (1) the stability of concept retrieval can be enhanced through dimensionality reduction via data aggregation, and (2) in shallow layers where gradient instability is more pronounced, gradient smoothing techniques are advised. Finally, our approach provides valuable insights into selecting the appropriate layer and concept representation dimensionality, paving the way towards CA in safety-critical XAI applications.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Canas, Antonio, Eva M. Ortigosa, Antonio F. Díaz e Julio Ortega. "XMLP: a Feed-Forward Neural Network with Two-Dimensional Layers and Partial Connectivity". In Artificial Neural Nets Problem Solving Methods, 89–96. Berlin, Heidelberg: Springer Berlin Heidelberg, 2003. http://dx.doi.org/10.1007/3-540-44869-1_12.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Kuljaca, Ognjen, Krunoslav Horvat e Jyotirmay Gadewadikar. "Adaptive Two Layers Neural Network Frequency Controller for Isolated Thermal Power System". In Technological Developments in Networking, Education and Automation, 203–7. Dordrecht: Springer Netherlands, 2010. http://dx.doi.org/10.1007/978-90-481-9151-2_35.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Tran, Van Quan. "Using Artificial Neural Network Containing Two Hidden Layers for Predicting Carbonation Depth of Concrete". In Lecture Notes in Civil Engineering, 1945–52. Singapore: Springer Singapore, 2021. http://dx.doi.org/10.1007/978-981-16-7160-9_197.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Liu, Chuan, Jiaqi Shen, Yue Ren e Hao Zheng. "Pipes of AI – Machine Learning Assisted 3D Modeling Design". In Proceedings of the 2020 DigitalFUTURES, 17–26. Singapore: Springer Singapore, 2021. http://dx.doi.org/10.1007/978-981-33-4400-6_2.

Texto completo da fonte

Resumo:

AbstractStyle transfer is a design technique that is based on Artificial Intelligence and Machine Learning, which is an innovative way to generate new images with the intervention of style images. The output image will carry the characteristic of style image and maintain the content of the input image. However, the design technique is employed in generating 2D images, which has a limited range in practical use. Thus, the goal of the project is to utilize style transfer as a toolset for architectural design and find out the possibility for a 3D modeling design. To implement style transfer into the research, floor plans of different heights are selected from a given design boundary and set as the content images, while a framework of a truss structure is set as the style image. Transferred images are obtained after processing the style transfer neural network, then the geometric images are translated into floor plans for new structure design. After the selection of the tilt angle and the degree of density, vertical components that connecting two adjacent layers are generated to be the pillars of the structure. At this stage, 2D style transferred images are successfully transformed into 3D geometries, which can be applied to the architectural design processes. Generally speaking, style transfer is an intelligent design tool that provides architects with a variety of choices of idea-generating. It has the potential to inspire architects at an early stage of design with not only 2D but also 3D format.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Trabalhos de conferências sobre o assunto "Two-layers neural networks"

Zhao, Qingye, Xin Chen, Yifan Zhang, Meng Sha, Zhengfeng Yang, Wang Lin, Enyi Tang, Qiguang Chen e Xuandong Li. "Synthesizing ReLU neural networks with two hidden layers as barrier certificates for hybrid systems". In HSCC '21: 24th ACM International Conference on Hybrid Systems: Computation and Control. New York, NY, USA: ACM, 2021. http://dx.doi.org/10.1145/3447928.3456638.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Luo, Ping. "EigenNet: Towards Fast and Structural Learning of Deep Neural Networks". In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/338.

Texto completo da fonte

Resumo:

Deep Neural Network (DNN) is difficult to train and easy to overfit in training. We address these two issues by introducing EigenNet, an architecture that not only accelerates training but also adjusts number of hidden neurons to reduce over-fitting. They are achieved by whitening the information flows of DNNs and removing those eigenvectors that may capture noises. The former improves conditioning of the Fisher information matrix, whilst the latter increases generalization capability. These appealing properties of EigenNet can benefit many recent DNN structures, such as network in network and inception, by wrapping their hidden layers into the layers of EigenNet. The modeling capacities of the original networks are preserved. Both the training wall-clock time and number of updates are reduced by using EigenNet, compared to stochastic gradient descent on various datasets, including MNIST, CIFAR-10, and CIFAR-100.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Jiang, Jianwen, Yuxuan Wei, Yifan Feng, Jingxuan Cao e Yue Gao. "Dynamic Hypergraph Neural Networks". In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/366.

Texto completo da fonte

Resumo:

In recent years, graph/hypergraph-based deep learning methods have attracted much attention from researchers. These deep learning methods take graph/hypergraph structure as prior knowledge in the model. However, hidden and important relations are not directly represented in the inherent structure. To tackle this issue, we propose a dynamic hypergraph neural networks framework (DHGNN), which is composed of the stacked layers of two modules: dynamic hypergraph construction (DHG) and hypergrpah convolution (HGC). Considering initially constructed hypergraph is probably not a suitable representation for data, the DHG module dynamically updates hypergraph structure on each layer. Then hypergraph convolution is introduced to encode high-order data relations in a hypergraph structure. The HGC module includes two phases: vertex convolution and hyperedge convolution, which are designed to aggregate feature among vertices and hyperedges, respectively. We have evaluated our method on standard datasets, the Cora citation network and Microblog dataset. Our method outperforms state-of-the-art methods. More experiments are conducted to demonstrate the effectiveness and robustness of our method to diverse data distributions.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Tominaga, Shaji. "Coordinate transformation of object colors using neural networks". In OSA Annual Meeting. Washington, D.C.: Optica Publishing Group, 1992. http://dx.doi.org/10.1364/oam.1992.tuq6.

Texto completo da fonte

Resumo:

Coordinate transformation between the Munsell and CIE-XYZ color systems is often needed in measuring and displaying object colors. No equation has been defined that specifies a direct transformation between two color spaces, but a table of data provides numerical correspondence between the two systems. So far, the transformation has been done by the complicated method of three-dimensional interpolation to this table of data. This paper proposes a new method of transformation using neural networks. A multilayer network is considered as a nonlinear transformer that adaptively learns a relationship between two color spaces. The complex mapping can then be executed rapidly by linking simple nonlinear units in parallel and in multilayers. The table of data is used for network learning by the back propagation method and for testing the performance. The input and output units correspond to three color coordinates in two color systems. A 3-10-10-10-3 type network with three hidden layers of 10 units is obtained as the most suitable one. The accuracy of transformation is examined on computer experiments. In our transformation method the database is not necessary, and the table of a large amount of data is replaced with about 300 weighting coefficients to link units in the network.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Kim, Myung Soo, e Clark C. Guest. "Opto-neural system for pattern classification". In OSA Annual Meeting. Washington, D.C.: Optica Publishing Group, 1990. http://dx.doi.org/10.1364/oam.1990.mjj3.

Texto completo da fonte

Resumo:

An optoneural system, which is a combination of an optical processor and a neural network, is developed for pattern classification. The system takes advantages of the two-dimensional processing capability of optics and the mapping capability of neural networks. The optical processor consists of a binary phase-only filter, and the neural network consists of three nonlinear mapping layers: the input layer, a hidden layer, and the output layer. Correlation outputs of the optical processor are used as inputs to the neural network. Binary phase in the binary phase-only filter and weights of the neural network are simultaneously trained with a simulated annealing algorithm. Gray-tone texture patterns that are not easily classified with annealed binary phase-only filters are well classified with the trained optoneural system.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Tong Zhao e Shaohua Qu. "Adaptive control for nonlinear systems with H^∞ tracking performance via two-layers neural networks". In 2008 IEEE International Conference on Automation and Logistics (ICAL). IEEE, 2008. http://dx.doi.org/10.1109/ical.2008.4636271.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Mkadem, F., M. Ben Ayed, S. Boumaiza, J. Wood e P. Aaen. "Behavioral modeling and digital predistortion of power amplifiers with memory using two hidden layers artificial neural networks". In 2010 IEEE/MTT-S International Microwave Symposium - MTT 2010. IEEE, 2010. http://dx.doi.org/10.1109/mwsym.2010.5514964.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Mkadem, Farouk, Morsi B. Ayed, Slim Boumaiza, John Wood e Peter Aaen. "Behavioral modeling and digital predistortion of Power Amplifiers with memory using Two Hidden Layers Artificial Neural Networks". In 2010 IEEE/MTT-S International Microwave Symposium - MTT 2010. IEEE, 2010. http://dx.doi.org/10.1109/mwsym.2010.5517039.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

MOUSAVI, MOHSEN, e AMIR H. GANDOMI. "TWO-DIMENSIONAL CONVOLUTIONAL NEURAL NETWORKS FOR WOOD QUALITY ASSESSMENT". In Structural Health Monitoring 2023. Destech Publications, Inc., 2023. http://dx.doi.org/10.12783/shm2023/36880.

Texto completo da fonte

Resumo:

Different materials, including wood, have been tested using the contact Ultrasonic Testing (UT) technique. The time and velocity of the ultrasonic wave in a wood section have traditionally been monitored and correlated with wood quality. This practice, however, has not yielded satisfactory results, prompting researchers to develop new strategies to address the issue. In this study, the primary objective is to employ convolutional neural networks (CNN) to assess wood quality using the results of contact ultrasonic testing. To this end, 2D CNN models are employed to train on labeled ultrasonic signals as the training set. The developed models are thus set to solve supervised classification problems based on data gathered from testing specimens with various health conditions. The tested specimens are two types of wood with and without natural imperfections. Therefore, the size and shape of damage are different across specimens-billets harvested from trees at two sites in NSW and WA, Australia. This study aims to visualize and investigate the properties of the features extracted by the inner layers of the developed CNN models. This way, an unsupervised strategy can be devised to solve the clustering problem of woods based on their health condition.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Dabetwar, Shweta, Stephen Ekwaro-Osire e João Paulo Dias. "Damage Detection of Composite Materials Using Data Fusion With Deep Neural Networks". In ASME Turbo Expo 2020: Turbomachinery Technical Conference and Exposition. American Society of Mechanical Engineers, 2020. http://dx.doi.org/10.1115/gt2020-15097.

Texto completo da fonte

Resumo:

Abstract Composite materials have enormous applications in various fields. Thus, it is important to have an efficient damage detection method to avoid catastrophic failures. Due to the existence of multiple damage modes and the availability of data in different formats, it is important to employ efficient techniques to consider all the types of damage. Deep neural networks were seen to exhibit the ability to address similar complex problems. The research question in this work is ‘Can data fusion improve damage classification using the convolutional neural network?’ The specific aims developed were to 1) assess the performance of image encoding algorithms, 2) classify the damage using data from separate experimental coupons, and 3) classify the damage using mixed data from multiple experimental coupons. Two different experimental measurements were taken from NASA Ames Prognostic Repository for Carbon Fiber Reinforced polymer. To use data fusion, the piezoelectric signals were converted into images using Gramian Angular Field (GAF) and Markov Transition Field. Using data fusion techniques, the input dataset was created for a convolutional neural network with three hidden layers to determine the damage states. The accuracies of all the image encoding algorithms were compared. The analysis showed that data fusion provided better results as it contained more information on the damages modes that occur in composite materials. Additionally, GAF was shown to perform the best. Thus, the combination of data fusion and deep neural network techniques provides an efficient method for damage detection of composite materials.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Relatórios de organizações sobre o assunto "Two-layers neural networks"

Tayeb, Shahab. Taming the Data in the Internet of Vehicles. Mineta Transportation Institute, janeiro de 2022. http://dx.doi.org/10.31979/mti.2022.2014.

Texto completo da fonte

Resumo:

As an emerging field, the Internet of Vehicles (IoV) has a myriad of security vulnerabilities that must be addressed to protect system integrity. To stay ahead of novel attacks, cybersecurity professionals are developing new software and systems using machine learning techniques. Neural network architectures improve such systems, including Intrusion Detection System (IDSs), by implementing anomaly detection, which differentiates benign data packets from malicious ones. For an IDS to best predict anomalies, the model is trained on data that is typically pre-processed through normalization and feature selection/reduction. These pre-processing techniques play an important role in training a neural network to optimize its performance. This research studies the impact of applying normalization techniques as a pre-processing step to learning, as used by the IDSs. The impacts of pre-processing techniques play an important role in training neural networks to optimize its performance. This report proposes a Deep Neural Network (DNN) model with two hidden layers for IDS architecture and compares two commonly used normalization pre-processing techniques. Our findings are evaluated using accuracy, Area Under Curve (AUC), Receiver Operator Characteristic (ROC), F-1 Score, and loss. The experimentations demonstrate that Z-Score outperforms no-normalization and the use of Min-Max normalization.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Arhin, Stephen, Babin Manandhar, Hamdiat Baba Adam e Adam Gatiba. Predicting Bus Travel Times in Washington, DC Using Artificial Neural Networks (ANNs). Mineta Transportation Institute, abril de 2021. http://dx.doi.org/10.31979/mti.2021.1943.

Texto completo da fonte

Resumo:

Washington, DC is ranked second among cities in terms of highest public transit commuters in the United States, with approximately 9% of the working population using the Washington Metropolitan Area Transit Authority (WMATA) Metrobuses to commute. Deducing accurate travel times of these metrobuses is an important task for transit authorities to provide reliable service to its patrons. This study, using Artificial Neural Networks (ANN), developed prediction models for transit buses to assist decision-makers to improve service quality and patronage. For this study, we used six months of Automatic Vehicle Location (AVL) and Automatic Passenger Counting (APC) data for six Washington Metropolitan Area Transit Authority (WMATA) bus routes operating in Washington, DC. We developed regression models and Artificial Neural Network (ANN) models for predicting travel times of buses for different peak periods (AM, Mid-Day and PM). Our analysis included variables such as number of served bus stops, length of route between bus stops, average number of passengers in the bus, average dwell time of buses, and number of intersections between bus stops. We obtained ANN models for travel times by using approximation technique incorporating two separate algorithms: Quasi-Newton and Levenberg-Marquardt. The training strategy for neural network models involved feed forward and errorback processes that minimized the generated errors. We also evaluated the models with a Comparison of the Normalized Squared Errors (NSE). From the results, we observed that the travel times of buses and the dwell times at bus stops generally increased over time of the day. We gathered travel time equations for buses for the AM, Mid-Day and PM Peaks. The lowest NSE for the AM, Mid-Day and PM Peak periods corresponded to training processes using Quasi-Newton algorithm, which had 3, 2 and 5 perceptron layers, respectively. These prediction models could be adapted by transit agencies to provide the patrons with accurate travel time information at bus stops or online.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Oferecemos descontos em todos os planos premium para autores cujas obras estão incluídas em seleções literárias temáticas. Contate-nos para obter um código promocional único!