IMPORT LIBRARY DEVELOPMENT APPROACH FOR NEURAL NETWORKS IN NNEF FORMAT FOR OPENVX STANDARD

There are many frameworks for building, training and executing neural networks. Each of them offers their own format for storing network architecture. There are two frameworks considered in this paper: Caffe and Torch. They offer Google Protocol Buffer (protobuf) and the built-in Torch format for storing the architecture of neural networks. The existence of different formats leads to the difficulties of porting neural networks to finite devices of different manufacturers. It leads to difficulties in porting neural networks to end-point devices of different vendors. To resolve these issues the Khronos Group proposed universal NNEF format which will be mediator between frameworks and proprietary low-level libraries. The NNEF format allows storing a description of a neural network using a computational graph. In this paper the two main approaches of development of import (parsing) library for neural networks stored in NNEF: online and offline parsing. For each approach an advantages and disadvantages were noticed which will help developers to choose correct way of NNEF parser implementation. The main advantage of an offline parser is simplicity for debugging, and the online parser is a low computational complexity.

Download Full-text

Selecting the architecture of a class of back-propagation neural networks used as approximators

Artificial intelligence for engineering design analysis and manufacturing ◽

10.1017/s0890060400001827 ◽

1997 ◽

Vol 11 (1) ◽

pp. 33-44 ◽

Cited By ~ 11

Author(s):

William C. Carpenter ◽

Margery E. Hoffman

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Architecture ◽

Back Propagation ◽

Region Of Interest ◽

Input Output ◽

Advantages And Disadvantages ◽

Back Propagation Neural Networks ◽

Input Layer ◽

Hidden Layer

AbstractThis paper examines the architecture of back-propagation neural networks used as approximators by addressing the interrelationship between the number of training pairs and the number of input, output, and hidden layer nodes required for a good approximation. It concentrates on nets with an input layer, one hidden layer, and one output layer. It shows that many of the currently proposed schemes for selecting network architecture for such nets are deficient. It demonstrates in numerous examples that overdetermined neural networks tend to give good approximations over a region of interest, while underdetermined networks give approximations which can satisfy the training pairs but may give poor approximations over that region of interest. A scheme is presented that adjusts the number of hidden layer nodes in a neural network so as to give an overdetermined approximation. The advantages and disadvantages of using multiple output nodes are discussed. Guidelines for selecting the number of output nodes are presented.

Download Full-text

RANDOM MULTI-MODAL DEEP LEARNING IN THE PROBLEM OF IMAGE RECOGNITION

ВЕСТНИК ВОРОНЕЖСКОГО ГОСУДАРСТВЕННОГО ТЕХНИЧЕСКОГО УНИВЕРСИТЕТА ◽

10.36622/vstu.2021.17.4.003 ◽

2021 ◽

pp. 21-26

Author(s):

А.И. Паршин ◽

М.Н. Аралов ◽

В.Ф. Барабанов ◽

Н.И. Гребенникова

Keyword(s):

Neural Network ◽

Machine Learning ◽

Neural Networks ◽

Image Recognition ◽

Recurrent Neural Networks ◽

Network Architecture ◽

Deep Neural Networks ◽

Machine Learning Algorithms ◽

Complex Data ◽

Advantages And Disadvantages

Задача распознавания изображений - одна из самых сложных в машинном обучении, требующая от исследователя как глубоких знаний, так и больших временных и вычислительных ресурсов. В случае использования нелинейных и сложных данных применяются различные архитектуры глубоких нейронных сетей, но при этом сложным вопросом остается проблема выбора нейронной сети. Основными архитектурами, используемыми повсеместно, являются свёрточные нейронные сети (CNN), рекуррентные нейронные сети (RNN), глубокие нейронные сети (DNN). На основе рекуррентных нейронных сетей (RNN) были разработаны сети с долгой краткосрочной памятью (LSTM) и сети с управляемыми реккурентными блоками (GRU). Каждая архитектура нейронной сети имеет свою структуру, свои настраиваемые и обучаемые параметры, обладает своими достоинствами и недостатками. Комбинируя различные виды нейронных сетей, можно существенно улучшить качество предсказания в различных задачах машинного обучения. Учитывая, что выбор оптимальной архитектуры сети и ее параметров является крайне трудной задачей, рассматривается один из методов построения архитектуры нейронных сетей на основе комбинации свёрточных, рекуррентных и глубоких нейронных сетей. Показано, что такие архитектуры превосходят классические алгоритмы машинного обучения The image recognition task is one of the most difficult in machine learning, requiring both deep knowledge and large time and computational resources from the researcher. In the case of using nonlinear and complex data, various architectures of deep neural networks are used but the problem of choosing a neural network remains a difficult issue. The main architectures used everywhere are convolutional neural networks (CNN), recurrent neural networks (RNN), deep neural networks (DNN). Based on recurrent neural networks (RNNs), Long Short Term Memory Networks (LSTMs) and Controlled Recurrent Unit Networks (GRUs) were developed. Each neural network architecture has its own structure, customizable and trainable parameters, and advantages and disadvantages. By combining different types of neural networks, you can significantly improve the quality of prediction in various machine learning problems. Considering that the choice of the optimal network architecture and its parameters is an extremely difficult task, one of the methods for constructing the architecture of neural networks based on a combination of convolutional, recurrent and deep neural networks is considered. We showed that such architectures are superior to classical machine learning algorithms

Download Full-text

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

Economy of Ukraine ◽

10.15407/economyukr.2020.10.054 ◽

2020 ◽

Vol 2020 (10) ◽

pp. 54-62

Author(s):

Oleksii VASYLIEV ◽

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Architecture ◽

Statistical Data ◽

Activation Function ◽

Decision Making Process ◽

Neural Network Architecture ◽

Acceptable Accuracy ◽

The Neural Network ◽

Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Download Full-text

Convolutional Neural Network for the Semantic Segmentation of Remote Sensing Images

Mobile Networks and Applications ◽

10.1007/s11036-020-01703-3 ◽

2021 ◽

Vol 26 (1) ◽

pp. 200-215

Author(s):

Muhammad Alam ◽

Jian-Feng Wang ◽

Cong Guangpei ◽

LV Yunrong ◽

Yuanfang Chen

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Neural Networks ◽

Image Processing ◽

Deep Learning ◽

Semantic Segmentation ◽

Natural Scene ◽

Remote Sensing Images ◽

Advantages And Disadvantages ◽

Target Segmentation

AbstractIn recent years, the success of deep learning in natural scene image processing boosted its application in the analysis of remote sensing images. In this paper, we applied Convolutional Neural Networks (CNN) on the semantic segmentation of remote sensing images. We improve the Encoder- Decoder CNN structure SegNet with index pooling and U-net to make them suitable for multi-targets semantic segmentation of remote sensing images. The results show that these two models have their own advantages and disadvantages on the segmentation of different objects. In addition, we propose an integrated algorithm that integrates these two models. Experimental results show that the presented integrated algorithm can exploite the advantages of both the models for multi-target segmentation and achieve a better segmentation compared to these two models.

Download Full-text

SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

ACM Transactions on Graphics ◽

10.1145/3450284 ◽

2021 ◽

Vol 40 (3) ◽

pp. 1-13

Author(s):

Lumin Yang ◽

Jiajie Zhuang ◽

Hongbo Fu ◽

Xiangzhi Wei ◽

Kun Zhou ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Architecture ◽

Large Scale ◽

State Of The Art ◽

Semantic Segmentation ◽

Structure Information ◽

Graph Neural Networks ◽

Node Labels ◽

Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

Download Full-text

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Sensors ◽

10.3390/s21082852 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2852

Author(s):

Parvathaneni Naga Srinivasu ◽

Jalluri Gnana SivaSai ◽

Muhammad Fazal Ijaz ◽

Akash Kumar Bhoi ◽

Wonjoon Kim ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Network ◽

Skin Disease ◽

Network Architecture ◽

Large Scale ◽

Short Term Memory ◽

Convolutional Networks ◽

Occurrence Matrix

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region’s image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

Download Full-text

Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

Journal of Fluid Mechanics ◽

10.1017/jfm.2016.615 ◽

2016 ◽

Vol 807 ◽

pp. 155-166 ◽

Cited By ~ 274

Author(s):

Julia Ling ◽

Andrew Kurzawski ◽

Jeremy Templeton

Keyword(s):

Neural Network ◽

Neural Networks ◽

Reynolds Stress ◽

Network Architecture ◽

Eddy Viscosity ◽

Deep Neural Networks ◽

Test Cases ◽

Neural Network Architecture ◽

Stress Anisotropy ◽

Anisotropy Tensor

There exists significant demand for improved Reynolds-averaged Navier–Stokes (RANS) turbulence models that are informed by and can represent a richer set of turbulence physics. This paper presents a method of using deep neural networks to learn a model for the Reynolds stress anisotropy tensor from high-fidelity simulation data. A novel neural network architecture is proposed which uses a multiplicative layer with an invariant tensor basis to embed Galilean invariance into the predicted anisotropy tensor. It is demonstrated that this neural network architecture provides improved prediction accuracy compared with a generic neural network architecture that does not embed this invariance property. The Reynolds stress anisotropy predictions of this invariant neural network are propagated through to the velocity field for two test cases. For both test cases, significant improvement versus baseline RANS linear eddy viscosity and nonlinear eddy viscosity models is demonstrated.

Download Full-text

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

Journal of Engineering for Gas Turbines and Power ◽

10.1115/1.2179465 ◽

2005 ◽

Vol 128 (4) ◽

pp. 773-782 ◽

Cited By ~ 13

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.

Download Full-text

Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia

Hydrology and Earth System Sciences ◽

10.5194/hess-16-1151-2012 ◽

2012 ◽

Vol 16 (4) ◽

pp. 1151-1169 ◽

Cited By ~ 34

Author(s):

A. El-Shafie ◽

A. Noureldin ◽

M. Taha ◽

A. Hussain ◽

M. Mukhlisin

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Model ◽

Neural Network Model ◽

Network Architecture ◽

Rainfall Time Series ◽

Hydrological Process ◽

Multi Layer Perceptron ◽

Rainfall Forecasting ◽

Unseen Data

Abstract. Rainfall is considered as one of the major components of the hydrological process; it takes significant part in evaluating drought and flooding events. Therefore, it is important to have an accurate model for rainfall forecasting. Recently, several data-driven modeling approaches have been investigated to perform such forecasting tasks as multi-layer perceptron neural networks (MLP-NN). In fact, the rainfall time series modeling involves an important temporal dimension. On the other hand, the classical MLP-NN is a static and has a memoryless network architecture that is effective for complex nonlinear static mapping. This research focuses on investigating the potential of introducing a neural network that could address the temporal relationships of the rainfall series. Two different static neural networks and one dynamic neural network, namely the multi-layer perceptron neural network (MLP-NN), radial basis function neural network (RBFNN) and input delay neural network (IDNN), respectively, have been examined in this study. Those models had been developed for the two time horizons for monthly and weekly rainfall forecasting at Klang River, Malaysia. Data collected over 12 yr (1997–2008) on a weekly basis and 22 yr (1987–2008) on a monthly basis were used to develop and examine the performance of the proposed models. Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static and dynamic neural networks. Results showed that the MLP-NN neural network model is able to follow trends of the actual rainfall, however, not very accurately. RBFNN model achieved better accuracy than the MLP-NN model. Moreover, the forecasting accuracy of the IDNN model was better than that of static network during both training and testing stages, which proves a consistent level of accuracy with seen and unseen data.

Download Full-text

Concatenated Convolutional Neural Network Model for Cuffless Blood Pressure Estimation Using Fuzzy Recurrence Properties of PPG Signals

10.21203/rs.3.rs-1231567/v1 ◽

2022 ◽

Author(s):

Ali Bahari Malayeri ◽

Mohammad Bagher Khodabakhshi

Keyword(s):

Neural Network ◽

Blood Pressure ◽

Neural Networks ◽

Network Architecture ◽

Spatial Information ◽

Recurrence Plot ◽

Estimation Model ◽

British Hypertension Society ◽

Blood Pressure Estimation ◽

Cuffless Blood Pressure

Abstract Due to the importance of continuous monitoring of blood pressure (BP) in controlling hypertension, the topic of cuffless blood pressure (BP) estimation has been widely studied in recent years. A most important approach is to explore the nonlinear mapping between the recorded peripheral signals and the BP values which is usually conducted by deep neural networks. Because of the sequence-based pseudo periodic nature of peripheral signals such as photoplethysmogram (PPG), a proper estimation model needed to be equipped with the 1-dimensional (1-D) and recurrent layers. This, in turn, limits the usage of 2-dimensional (2-D) layers adopted in convolutional neural networks (CNN) for embedding spatial information in the model. In this study, considering the advantage of chaotic approaches, the recurrence characterization of peripheral signals was taken into account by a visual 2-D representation of PPG in phase space through fuzzy recurrence plot (FRP). FRP not only provides a beneficial framework for capturing the spatial properties of input signals but also creates a reliable approach for embedding the pseudo periodic properties to the neural models without using recurrent layers. Moreover, this study proposes a novel deep neural network architecture that combines the morphological features extracted simultaneously from two upgraded 1-D and 2-D CNNs capturing the temporal and spatial dependencies of PPGs in systolic and diastolic BP estimation. The model has been fed with the 1-D PPG sequences and the corresponding 2-D FRPs from two separate routes. The performance of the proposed framework was examined on the well-known public dataset, namely, Multi-Parameter Intelligent in Intensive Care II. Our scheme is analyzed and compared with the literature in terms of the requirements of the standards set by the British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI). The proposed model met the AAMI requirements, and it achieved a grade of A as stated by the BHS standard. In addition, its mean absolute errors (MAE) and standard deviation for both systolic and diastolic blood pressure estimations were considerably low, 3.05±5.26 mmHg and 1.58±2.6 mmHg, in turn.

Download Full-text