ANALOG HARDWARE IMPLEMENTATIONS OF ARTIFICIAL NEURAL NETWORKS

2011 ◽  
Vol 20 (03) ◽  
pp. 349-373 ◽  
Author(s):  
NADIA NEDJAH ◽  
RODRIGO MARTINS DA SILVA ◽  
LUIZA DE MACEDO MOURELLE
Keyword(s):  
Computing System ◽  
Activation Function ◽  
Lookup Table ◽  
Training Process ◽  
Systems Software ◽  
Hardware Implementations ◽  
Intrinsic Parallelism ◽  
Software Implementations ◽  
Analog Implementation ◽  
Artificial Neural

There are several possible implementations of artificial neural network that are based either on software or hardware systems. Software implementations are rather inefficient due to the fact that the intrinsic parallelism of the underlying computation is usually not taken advantage of in a mono-processor kind of computing system. Existing hardware implementations of ANNs are efficient as the dedicated datapath used is optimized and the hardware is usually parallel. Hardware implementations of ANNs may be either digital, analog, or even hybrid. Digital implementations of ANNs tend to be of high complexity, thus of high cost, and somehow imprecise due to the use of lookup table for the activation function. On the other hand, analog implementation of ANNs are generally very simple and much more precise. In this paper, we focus on possible analog implementations of ANNs. The neuron is based on a simple operational amplifier. The reviewed implementations allow for the use of both negative and positive synaptic weights. An alternative implementation permits the realization of the training process.

scholarly journals Evolvable Block-Based Neural Network Design for Applications in Dynamic Environments

VLSI Design ◽  
2010 ◽  
Vol 2010 ◽  
pp. 1-25 ◽  
Author(s):  
Saumil G. Merchant ◽  
Gregory D. Peterson
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Dynamic Environments ◽  
Hardware Implementations ◽  
Internal Parameters ◽  
Software Implementations ◽  
Power Operation ◽  
Artificial Neural ◽  
Block Based ◽  
Typical Design

Dedicated hardware implementations of artificial neural networks promise to provide faster, lower-power operation when compared to software implementations executing on microprocessors, but rarely do these implementations have the flexibility to adapt and train online under dynamic conditions. A typical design process for artificial neural networks involves offline training using software simulations and synthesis and hardware implementation of the obtained network offline. This paper presents a design of block-based neural networks (BbNNs) on FPGAs capable of dynamic adaptation and online training. Specifically the network structure and the internal parameters, the two pieces of the multiparametric evolution of the BbNNs, can be adapted intrinsically, in-field under the control of the training algorithm. This ability enables deployment of the platform in dynamic environments, thereby significantly expanding the range of target applications, deployment lifetimes, and system reliability. The potential and functionality of the platform are demonstrated using several case studies.

scholarly journals Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yongil Cho ◽  
Jong Soo Kim ◽  
Tae Ho Lim ◽  
Inhye Lee ◽  
Jongbong Choi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Activation Function ◽  
X Rays ◽  
Training Process ◽  
X Ray ◽  
Chest X Ray ◽  
Artificial Neural ◽  
Fully Connected ◽  
Better Than

AbstractThe purpose of this study was to evaluate the diagnostic performance achieved by using fully-connected small artificial neural networks (ANNs) and a simple training process, the Kim-Monte Carlo algorithm, to detect the location of pneumothorax in chest X-rays. A total of 1,000 chest X-ray images with pneumothorax were taken randomly from NIH (the National Institutes of Health) public image database and used as the training and test sets. Each X-ray image with pneumothorax was divided into 49 boxes for pneumothorax localization. For each of the boxes in the chest X-ray images contained in the test set, the area under the receiver operating characteristic (ROC) curve (AUC) was 0.882, and the sensitivity and specificity were 80.6% and 83.0%, respectively. In addition, a common currently used deep-learning method for image recognition, the convolution neural network (CNN), was also applied to the same dataset for comparison purposes. The performance of the fully-connected small ANN was better than that of the CNN. Regarding the diagnostic performances of the CNN with different activation functions, the CNN with a sigmoid activation function for fully-connected hidden nodes was better than the CNN with the rectified linear unit (RELU) activation function. This study showed that our approach can accurately detect the location of pneumothorax in chest X-rays, significantly reduce the time delay incurred when diagnosing urgent diseases such as pneumothorax, and increase the effectiveness of clinical practice and patient care.

scholarly journals Prediction of Stress in Power Transformer Winding Conductors Using Artificial Neural Networks: Hyperparameter Analysis

Energies ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 4242
Author(s):  
Fausto Valencia ◽  
Hugo Arcos ◽  
Franklin Quilumba
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Power Transformer ◽  
Network Models ◽  
Activation Function ◽  
Neural Network Models ◽  
Transformer Winding ◽  
Artificial Neural ◽  
Femm Software

The purpose of this research is the evaluation of artificial neural network models in the prediction of stresses in a 400 MVA power transformer winding conductor caused by the circulation of fault currents. The models were compared considering the training, validation, and test data errors’ behavior. Different combinations of hyperparameters were analyzed based on the variation of architectures, optimizers, and activation functions. The data for the process was created from finite element simulations performed in the FEMM software. The design of the Artificial Neural Network was performed using the Keras framework. As a result, a model with one hidden layer was the best suited architecture for the problem at hand, with the optimizer Adam and the activation function ReLU. The final Artificial Neural Network model predictions were compared with the Finite Element Method results, showing good agreement but with a much shorter solution time.

scholarly journals Using Artificial Neural Networks in Predicting the Level of Stress among Military Conscripts

Mathematics ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 626
Author(s):  
Svajone Bekesiene ◽  
Rasa Smaliukiene ◽  
Ramute Vaicaitiene
Keyword(s):  
Neural Network ◽  
Transfer Functions ◽  
Back Propagation ◽  
Armed Forces ◽  
Activation Function ◽  
Optimal Number ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Classification Rate ◽  
Artificial Neural

The present study aims to elucidate the main variables that increase the level of stress at the beginning of military conscription service using an artificial neural network (ANN)-based prediction model. Random sample data were obtained from one battalion of the Lithuanian Armed Forces, and a survey was conducted to generate data for the training and testing of the ANN models. Using nonlinearity in stress research, numerous ANN structures were constructed and verified to limit the optimal number of neurons, hidden layers, and transfer functions. The highest accuracy was obtained by the multilayer perceptron neural network (MLPNN) with a 6-2-2 partition. A standardized rescaling method was used for covariates. For the activation function, the hyperbolic tangent was used with 20 units in one hidden layer as well as the back-propagation algorithm. The best ANN model was determined as the model that showed the smallest cross-entropy error, the correct classification rate, and the area under the ROC curve. These findings show, with high precision, that cohesion in a team and adaptation to military routines are two critical elements that have the greatest impact on the stress level of conscripts.

Improving Accuracy using The ASERLU layer in CNN-BiLSTM Architecture on Sentiment Analysis

2021 ◽  
Vol 5 (5) ◽  
pp. 1001-1007
Author(s):  
Sandi Hermawan ◽  
Rilla Mandala
Keyword(s):  
United States ◽  
Activation Function ◽  
The United States ◽  
Activation Method ◽  
Training Process ◽  
Educational Backgrounds ◽  
User Comments ◽  
Sentiment Detection ◽  
Improving Accuracy ◽  
Different Cultures

There have been 350,000 tweets generated by the interaction of social networks with different cultures and educational backgrounds in the last ten years. Various sentiments are expressed in the user comments, from support to hatred. The sentiments regarded the United States General Election in 2020. This dataset has 3,000 data gotten from previous research. We augment it becomes 15,000 data to facilitate training and increase the required data. Sentiment detection is carried out using the CNN-BiLSTM architecture. It is chosen because CNN can filter essential words, and BiLSTM can remember memory in two directions. By utilizing both, the training process becomes maximum. However, this method has disadvantages in the activation. The drawback of the existing activation method, i.e., "Zero-hard Rectifier" and "ReLU Dropout" problem to become the cause of training stopped in the ReLU activation, and the exponential function cannot be set become the activation function still rigid towards output value in the SERLU activation. To overcome this problem, we propose a novel activation method to repair activation in CNN-BiLSTM architecture. It is namely the ASERLU activation function. It can adjust positive value output, negative value output, and exponential value by the setter variables. So, it adapts more conveniently to the output value and becomes a flexible activation function because it can be increased and decreased as needed. It is the first research applied in architecture. Compared with ReLU and SERLU, our proposed method gives higher accuracy based on the experiment results.

scholarly journals Modeling of Stage-Discharge Using Back Propagation ANN, ANFIS, and WANN-based Computing Technique

2021 ◽  
Author(s):  
Ravi Shukla ◽  
Pravendra Kumar ◽  
Dinesh Kumar Vishwakarma ◽  
Rawshan Ali ◽  
Rohitashw Kumar ◽  
...  
Keyword(s):  
Water Resource Management ◽  
Hydrological Modeling ◽  
Fuzzy Inference ◽  
Back Propagation ◽  
Activation Function ◽  
Neural System ◽  
Back Propagation Algorithm ◽  
Inference System ◽  
Computing Technique ◽  
Artificial Neural

Abstract The development of the stage-discharge relationship is a fundamental issue in hydrological modeling. Due to the complexity of the stage-discharge relationship, discharge prediction plays an essential role in planning and water resource management. The present study was conducted for modeling of discharge at the Gaula barrage site in Uttarakhand state of India. The study evaluated, Adaptive Neuro-Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN) and Wavelet-Based Artificial Neural System (WANN) based models to estimate the discharge. The daily data of 12 years (2007-2018) were used to train and test the models. The Gamma test was used to identify the best model for discharge prediction. The input data having a stage with one-day lag and discharge with one and two-days lag and current-day discharge as output was used for discharge modeling. In the case of ANN models, the back-propagation algorithm and hyperbolic tangent sigmoid activation function was used. WANN used Haar, a trous based wavelet function. In ANFIS models, triangular, psig, generalized bell, and Gaussian membership functions were used to train and test the models. The models were evaluated qualitatively and quantitatively using correlation coefficient, root means square error, Willmott index, and coefficient of efficiency. It was found that ANFIS model performed better than ANN and WANN-based models for discharge prediction at the Gaula barrage.

scholarly journals Modeling of daily runoff from a small agricultural watershed using artificial neural network with resampling techniques

2014 ◽  
Vol 17 (1) ◽  
pp. 56-74 ◽  
Author(s):  
Gurjeet Singh ◽  
Rabindra K. Panda ◽  
Marc Lamers
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Agricultural Watershed ◽  
Training Data ◽  
Optimum Number ◽  
Training Process ◽  
Data Set ◽  
Reported Study ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The reported study was undertaken in a small agricultural watershed, namely, Kapgari in Eastern India having a drainage area of 973 ha. The watershed was subdivided into three sub-watersheds on the basis of drainage network and land topography. An attempt was made to relate the continuously monitored runoff data from the sub-watersheds and the whole-watershed with the rainfall and temperature data using the artificial neural network (ANN) technique. The reported study also evaluated the bias in the prediction of daily runoff with shorter length of training data set using different resampling techniques with the ANN modeling. A 10-fold cross-validation (CV) technique was used to find the optimum number of hidden neurons in the hidden layer and to avoid neural network over-fitting during the training process for shorter length of data. The results illustrated that the ANN models developed with shorter length of training data set avoid neural network over-fitting during the training process, using a 10-fold CV method. Moreover, the biasness was investigated using the bootstrap resampling technique based ANN (BANN) for short length of training data set. In comparison with the 10-fold CV technique, the BANN is more efficient in solving the problems of the over-fitting and under-fitting during training of models for shorter length of data set.

Dynamic Control of Computation Consistency in the Parallel Dataflow Computing System

2021 ◽  
Vol 27 (12) ◽  
pp. 625-633
Author(s):  
N. N. Levchenko ◽  
◽  
D. N. Zmejev ◽  
Keyword(s):  
Computational Model ◽  
High Performance ◽  
Dynamic Control ◽  
Computing System ◽  
Computational Process ◽  
Computing Systems ◽  
Systems Software ◽  
Dataflow Computing

When developing high-performance multiprocessor computing systems, much attention is paid to ensuring uninterrupted operation, both in terms of hardware and software. In traditional computing systems, software is the main focus in address­ing these issues. The article discusses the solution to the issue of ensuring uninterrupted operation for the parallel dataflow computing system (PDCS), which implements the dataflow computational model with a dynamically formed context. Due to the features of the PDCS, it is proposed to implement this type of control in hardware, which will increase its efficiency, since the computational process will be controlled in dynamics, and not only in statics.

Analysis of Fin-Tube Evaporator Performance With Limited Experimental Data Using Artificial Neural Networks

2000 ◽  
Author(s):  
Arturo Pacheco-Vega ◽  
Mihir Sen ◽  
Rodney L. McClain
Keyword(s):  
Neural Network ◽  
Heat Rate ◽  
Network Models ◽  
Activation Function ◽  
Operating Conditions ◽  
Training Data ◽  
Neural Network Models ◽  
The Neural Network ◽  
Artificial Neural ◽  
Fin Tube

Abstract In the current study we consider the problem of accuracy in heat rate estimations from artificial neural network models of heat exchangers used for refrigeration applications. The network configuration is of the feedforward type with a sigmoid activation function and a backpropagation algorithm. Limited experimental measurements from a manufacturer are used to show the capability of the neural network technique in modeling the heat transfer in these systems. Results from this exercise show that a well-trained network correlates the data with errors of the same order as the uncertainty of the measurements. It is also shown that the number and distribution of the training data are linked to the performance of the network when estimating the heat rates under different operating conditions, and that networks trained from few tests may give large errors. A methodology based on the cross-validation technique is presented to find regions where not enough data are available to construct a reliable neural network. The results from three tests show that the proposed methodology gives an upper bound of the estimated error in the heat rates.

Power Forecasting from Solar Panels Using Artificial Neural Network in UTHM Parit Raja

2021 ◽  
Vol 02 (01) ◽  
Author(s):  
Natasha Munirah Mohd Fahmi ◽  
◽  
Nor Aira Zambri ◽  
Norhafiz Salim ◽  
Sim Sy Yi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Climatic Factors ◽  
Activation Function ◽  
Solar Panels ◽  
Ann Model ◽  
Power Characteristics ◽  
Step Procedure ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

This paper presents a step-by-step procedure for the simulation of photovoltaic modules with numerical values, using MALTAB/Simulink software. The proposed model is developed based on the mathematical model of PV module, which based on PV solar cell employing one-diode equivalent circuit. The output current and power characteristics curves highly depend on some climatic factors such as radiation and temperature, are obtained by simulation of the selected module. The collected data are used in developing Artificial Neural Network (ANN) model. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) are the techniques used to forecast the outputs of the PV. Various types of activation function will be applied such as Linear, Logistic Sigmoid, Hyperbolic Tangent Sigmoid and Gaussian. The simulation results show that the Logistic Sigmoid is the best technique which produce minimal root mean square error for the system.

Sign in / Sign up

Export Citation Format

Share Document