scholarly journals The Generalization Complexity Measure for Continuous Input Data

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Iván Gómez ◽  
Sergio A. Cannas ◽  
Omar Osenda ◽  
José M. Jerez ◽  
Leonardo Franco
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Input Data ◽  
Continuous Functions ◽  
Complexity Measure ◽  
Data Sets ◽  
Practical Case ◽  
Real World Data ◽  
Continuous Input ◽  
Hidden Layer

We introduce in this work an extension for the generalization complexity measure to continuous input data. The measure, originally defined in Boolean space, quantifies the complexity of data in relationship to the prediction accuracy that can be expected when using a supervised classifier like a neural network, SVM, and so forth. We first extend the original measure for its use with continuous functions to later on, using an approach based on the use of the set of Walsh functions, consider the case of having a finite number of data points (inputs/outputs pairs), that is, usually the practical case. Using a set of trigonometric functions a model that gives a relationship between the size of the hidden layer of a neural network and the complexity is constructed. Finally, we demonstrate the application of the introduced complexity measure, by using the generated model, to the problem of estimating an adequate neural network architecture for real-world data sets.

Mixture Models Based on Neural Network Averaging

2006 ◽  
Vol 18 (1) ◽  
pp. 1-9 ◽  
Author(s):  
Walter W. Focke
Keyword(s):  
Neural Network ◽  
Transfer Function ◽  
Mixture Model ◽  
Network Architecture ◽  
Binary Data ◽  
Data Sets ◽  
Wilson Equation ◽  
Power Mean ◽  
Hidden Layer ◽  
Box Cox Transformation

A modified version of the single hidden-layer perceptron architecture is proposed for modeling mixtures. A particular flexible mixture model is obtained by implementing the Box-Cox transformation as transfer function. In this case, the network response can be expressed in closed form as a weighted power mean. The quadratic Scheffé K-polynomial and the exponential Wilson equation turn out to be special forms of this general mixture model. Advantages of the proposed network architecture are that binary data sets suffice for “training” and that it is readily extended to incorporate additional mixture components while retaining all previously determined weights.

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

scholarly journals Image reconstruction through a multimode fiber with a simple neural network architecture

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Changyan Zhu ◽  
Eng Aik Chan ◽  
You Wang ◽  
Weina Peng ◽  
Ruixiang Guo ◽  
...  
Keyword(s):  
Neural Network ◽  
Image Reconstruction ◽  
Network Architecture ◽  
Neural Network Architecture ◽  
Training Time ◽  
Modal Dispersion ◽  
Multimode Fibers ◽  
Speckle Patterns ◽  
Hidden Layer ◽  
Simple Neural Network

AbstractMultimode fibers (MMFs) have the potential to carry complex images for endoscopy and related applications, but decoding the complex speckle patterns produced by mode-mixing and modal dispersion in MMFs is a serious challenge. Several groups have recently shown that convolutional neural networks (CNNs) can be trained to perform high-fidelity MMF image reconstruction. We find that a considerably simpler neural network architecture, the single hidden layer dense neural network, performs at least as well as previously-used CNNs in terms of image reconstruction fidelity, and is superior in terms of training time and computing resources required. The trained networks can accurately reconstruct MMF images collected over a week after the cessation of the training set, with the dense network performing as well as the CNN over the entire period.

scholarly journals A data-driven neural network architecture for sentiment analysis

2019 ◽  
Vol 53 (1) ◽  
pp. 2-19 ◽  
Author(s):  
Erion Çano ◽  
Maurizio Morisio
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Network Architecture ◽  
Network Models ◽  
Data Sets ◽  
Feature Maps ◽  
Neural Network Architecture ◽  
Neural Network Models ◽  
Content Type ◽  
Max Pooling

Purpose The fabulous results of convolution neural networks in image-related tasks attracted attention of text mining, sentiment analysis and other text analysis researchers. It is, however, difficult to find enough data for feeding such networks, optimize their parameters, and make the right design choices when constructing network architectures. The purpose of this paper is to present the creation steps of two big data sets of song emotions. The authors also explore usage of convolution and max-pooling neural layers on song lyrics, product and movie review text data sets. Three variants of a simple and flexible neural network architecture are also compared. Design/methodology/approach The intention was to spot any important patterns that can serve as guidelines for parameter optimization of similar models. The authors also wanted to identify architecture design choices which lead to high performing sentiment analysis models. To this end, the authors conducted a series of experiments with neural architectures of various configurations. Findings The results indicate that parallel convolutions of filter lengths up to 3 are usually enough for capturing relevant text features. Also, max-pooling region size should be adapted to the length of text documents for producing the best feature maps. Originality/value Top results the authors got are obtained with feature maps of lengths 6–18. An improvement on future neural network models for sentiment analysis could be generating sentiment polarity prediction of documents using aggregation of predictions on smaller excerpt of the entire text.

Fourier Neural Networks and Generalized Single Hidden Layer Networks in Aircraft Engine Fault Diagnostics

2005 ◽  
Vol 128 (4) ◽  
pp. 773-782 ◽  
Author(s):  
H. S. Tan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Fourier Transforms ◽  
Aircraft Engine ◽  
Fault Classification ◽  
Noise Robustness ◽  
Fault Diagnostics ◽  
Multiple Faults ◽  
Hidden Layer

The conventional approach to neural network-based aircraft engine fault diagnostics has been mainly via multilayer feed-forward systems with sigmoidal hidden neurons trained by back propagation as well as radial basis function networks. In this paper, we explore two novel approaches to the fault-classification problem using (i) Fourier neural networks, which synthesizes the approximation capability of multidimensional Fourier transforms and gradient-descent learning, and (ii) a class of generalized single hidden layer networks (GSLN), which self-structures via Gram-Schmidt orthonormalization. Using a simulation program for the F404 engine, we generate steady-state engine parameters corresponding to a set of combined two-module deficiencies and require various neural networks to classify the multiple faults. We show that, compared to the conventional network architecture, the Fourier neural network exhibits stronger noise robustness and the GSLNs converge at a much superior speed.

scholarly journals Input data preprocessing method for exchange rate forecasting via neural network

2014 ◽  
Vol 11 (4) ◽  
pp. 597-608
Author(s):  
Dragan Antic ◽  
Miroslav Milovanovic ◽  
Stanisa Peric ◽  
Sasa Nikolic ◽  
Marko Milojkovic
Keyword(s):  
Neural Network ◽  
Input Data ◽  
Principal Component ◽  
Economic Systems ◽  
Data Sets ◽  
Foreign Exchange Rates ◽  
Analysis Method ◽  
Feed Forward Neural Network ◽  
Parameters Selection ◽  
Neural Network Input

The aim of this paper is to present a method for neural network input parameters selection and preprocessing. The purpose of this network is to forecast foreign exchange rates using artificial intelligence. Two data sets are formed for two different economic systems. Each system is represented by six categories with 70 economic parameters which are used in the analysis. Reduction of these parameters within each category was performed by using the principal component analysis method. Component interdependencies are established and relations between them are formed. Newly formed relations were used to create input vectors of a neural network. The multilayer feed forward neural network is formed and trained using batch training. Finally, simulation results are presented and it is concluded that input data preparation method is an effective way for preprocessing neural network data.

ARTIFICIAL NEURAL NETWORK (ANN)-BASED PREDICTIVE TOOL FOR ESTIMATING LIGHTNING DAMAGE IN COMPOSITES

2021 ◽  
Author(s):  
DEVIN NIELSEN ◽  
TYLER LOTT ◽  
SOM DUTTA ◽  
JUHYEONG LEE
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Architecture ◽  
Back Propagation ◽  
Training Dataset ◽  
Predictive Tool ◽  
Ann Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer

In this study, three artificial neural network (ANN) models are developed with back propagation (BP) optimization algorithms to predict various lightning damage modes in carbon/epoxy laminates. The proposed ANN models use three input variables associated with lightning waveform parameters (i.e., the peak current amplitude, rising time, and decaying time) to predict fiber damage, matrix damage, and through-thickness damage in the composites. The data used for training and testing the networks was actual lightning damage data collected from peer-reviewed published literature. Various BP training algorithms and network architecture configurations (i.e., data splitting, the number of neurons in a hidden layer, and the number of hidden layers) have been tested to improve the performance of the neural networks. Among the various BP algorithms considered, the Bayesian regularization back propagation (BRBP) showed the overall best performance in lightning damage prediction. When using the BRBP algorithm, as expected, the greater the fraction of the collected data that is allocated to the training dataset, the better the network is trained. In addition, the optimal ANN architecture was found to have a single hidden layer with 20 neurons. The ANN models proposed in this work may prove useful in preliminary assessments of lightning damage and reduce the number of expensive experimental lightning tests.

scholarly journals Application of Long Short-Term Memory (LSTM) Neural Network for Flood Forecasting

Water ◽  
2019 ◽  
Vol 11 (7) ◽  
pp. 1387 ◽  
Author(s):  
Le ◽  
Ho ◽  
Lee ◽  
Jung
Keyword(s):  
Neural Network ◽  
River Basin ◽  
Input Data ◽  
Short Term Memory ◽  
Flood Forecasting ◽  
Data Sets ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Hoa Binh

Flood forecasting is an essential requirement in integrated water resource management. This paper suggests a Long Short-Term Memory (LSTM) neural network model for flood forecasting, where the daily discharge and rainfall were used as input data. Moreover, characteristics of the data sets which may influence the model performance were also of interest. As a result, the Da River basin in Vietnam was chosen and two different combinations of input data sets from before 1985 (when the Hoa Binh dam was built) were used for one-day, two-day, and three-day flowrate forecasting ahead at Hoa Binh Station. The predictive ability of the model is quite impressive: The Nash–Sutcliffe efficiency (NSE) reached 99%, 95%, and 87% corresponding to three forecasting cases, respectively. The findings of this study suggest a viable option for flood forecasting on the Da River in Vietnam, where the river basin stretches between many countries and downstream flows (Vietnam) may fluctuate suddenly due to flood discharge from upstream hydroelectric reservoirs.

Predicting Fatigue Life of Pre-Corroded LC4 Aluminum Alloy by Artificial Neural Network

2010 ◽  
Vol 118-120 ◽  
pp. 221-225 ◽  
Author(s):  
Cheng Long Xu ◽  
Sheng Li Lv ◽  
Zhen Guo Wang ◽  
Wei Zhang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Aluminum Alloy ◽  
Fatigue Life ◽  
Network Architecture ◽  
Fatigue Tests ◽  
Data Sets ◽  
Absolute Relative Error ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The purpose of this work was to predict the fatigue life of pre-corroded LC4 aluminum alloy by applying artificial neural network (ANN). Specimens were exposed to the same corrosive environment for 24h, 48h, and 72h. Fatigue tests were conducted under different stress levels. The existing experimental data sets were used for training and testing the construction of proposed network. A suitable network architecture (2-15-1) was proposed with good performance in this study. For evaluating the method efficiency, the experimental results have been compared to values predicted by ANN. The maximum absolute relative error for predicted values does not exceed 5%. Therefore it can be concluded that using neural networks to predict the fatigue life of LC4 is feasible and reliable.

Prediction of Yarn Quality Based on BP Neural Network

2011 ◽  
Vol 331 ◽  
pp. 449-453
Author(s):  
Jing Yuan ◽  
Ying Lin Li ◽  
Su Ying Chen
Keyword(s):  
Neural Network ◽  
Mathematical Models ◽  
Network Architecture ◽  
Raw Materials ◽  
Nonlinear Approximation ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Yarn Quality ◽  
Spinning Process ◽  
Hidden Layer

As the quality of yarn and the fiber indicators are nonlinear relationship, the traditional mathematical models or empirical formula has been unable to accurately resolve the problem. In view of artificial neural networks do not need to build accurate mathematical models, applicable to solving the problem of yarn quality prediction. In this paper, good nonlinear approximation ability of BP (Back Propagation) neural network be used, the use of neural network toolbox of MATLAB functions for modeling, good results was obtained. Prediction model set a hidden layer, using three-tier network architecture, and take the input layer 4 nodes, hidden layer 8 nodes and output layer 2 nodes. According to forecast results, can ensure the yarn quality effectively, use of raw materials rationally, to achieve optimal distribution of cotton. Meanwhile, the spinning process design can also be provided validation, for the development of new products to provide a theoretical basis.

Sign in / Sign up

Export Citation Format

Share Document