Neuromorphic Functional Modules of Spiking Neural Network

2021 ◽  
Vol 23 (6) ◽  
pp. 317-326
Author(s):  
E.A. Ryndin ◽  
◽  
N.V. Andreeva ◽  
V.V. Luchinin ◽  
K.S. Goncharov ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Synaptic Plasticity ◽  
Data Processing ◽  
Circuit Design ◽  
Spiking Neural Networks ◽  
Spiking Neural Network ◽  
Wide Range ◽  
Artificial Neural

In the current era, design and development of artificial neural networks exploiting the architecture of the human brain have evolved rapidly. Artificial neural networks effectively solve a wide range of common for artificial intelligence tasks involving data classification and recognition, prediction, forecasting and adaptive control of object behavior. Biologically inspired underlying principles of ANN operation have certain advantages over the conventional von Neumann architecture including unsupervised learning, architectural flexibility and adaptability to environmental change and high performance under significantly reduced power consumption due to heavy parallel and asynchronous data processing. In this paper, we present the circuit design of main functional blocks (neurons and synapses) intended for hardware implementation of a perceptron-based feedforward spiking neural network. As the third generation of artificial neural networks, spiking neural networks perform data processing utilizing spikes, which are discrete events (or functions) that take place at points in time. Neurons in spiking neural networks initiate precisely timing spikes and communicate with each other via spikes transmitted through synaptic connections or synapses with adaptable scalable weight. One of the prospective approach to emulate the synaptic behavior in hardware implemented spiking neural networks is to use non-volatile memory devices with analog conduction modulation (or memristive structures). Here we propose a circuit design for functional analogues of memristive structure to mimic a synaptic plasticity, pre- and postsynaptic neurons which could be used for developing circuit design of spiking neural network architectures with different training algorithms including spike-timing dependent plasticity learning rule. Two different circuits of electronic synapse were developed. The first one is an analog synapse with photoresistive optocoupler used to ensure the tunable conductivity for synaptic plasticity emulation. While the second one is a digital synapse, in which the synaptic weight is stored in a digital code with its direct conversion into conductivity (without digital-to-analog converter andphotoresistive optocoupler). The results of the prototyping of developed circuits for electronic analogues of synapses, pre- and postsynaptic neurons and the study of transient processes are presented. The developed approach could provide a basis for ASIC design of spiking neural networks based on CMOS (complementary metal oxide semiconductor) design technology.

Enhanced interpretation of magnetic survey data from archaeological sites using artificial neural networks

Geophysics ◽  
2006 ◽  
Vol 71 (5) ◽  
pp. H45-H53 ◽  
Author(s):  
David. J. Bescoby ◽  
Gavin C. Cawley ◽  
P. Neil Chroston
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Data Processing ◽  
Survey Data ◽  
Source Parameters ◽  
Magnetic Data ◽  
Burial Depth ◽  
Training Procedure ◽  
Wide Range ◽  
Artificial Neural

The use of magnetic surveys for archaeological prospecting is a well-established and versatile technique, and a wide range of data processing routines are often applied to further enhance acquired data or derive source parameters. Of particular interest in this respect is the application of artificial neural networks (ANNs) to predict source parameters such as the burial depths of detected features of interest. Within this study, ANNs based upon a multilayer perceptron architecture are used to perform the nonlinear mapping between buried wall features detected within the magnetic data and their corresponding burial depth for surveys in the ancient city of Butrint in southern Albania, achieving a greater level of information from the survey data. Suitable network training examples and test data were generated using forward models based upon ground-truth observations. The training procedure adopts a supervised learning routine that is optimized using a conjugate gradient method, while the learning algorithm also prunes network elements to prevent overregularization by reducing model complexity. Data processing was further enhanced by introducing rotational invariance using Zernike moments and by utilizing the combined output of a number, or committee, of networks. When applied to a section of survey data from Butrint, the ANN routine successfully predicted the burial depth of a number of detected wall features, with an rms error on the order of [Formula: see text], and provided a coherent map of the buried building foundations. The neural network approach offered advantages in terms of efficiency and flexibility over more conventional data-inversion techniques within the context of the study, giving fast solutions for large, complex data sets while having high noise tolerance.

scholarly journals Deep Convolutional Spiking Neural Networks for Image Classification

2021 ◽  
Author(s):  
Ruthvik Vaila
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Gradient Descent ◽  
Stochastic Gradient ◽  
Spiking Neural Networks ◽  
Stochastic Gradient Descent ◽  
Data Set ◽  
Learning Capabilities ◽  
Artificial Neural

Spiking neural networks are biologically plausible counterparts of artificial neural networks. Artificial neural networks are usually trained with stochastic gradient descent (SGD) and spiking neural networks are trained with bioinspired spike timing dependent plasticity (STDP). Spiking networks could potentially help in reducing power usage owing to their binary activations. In this work, we use unsupervised STDP in the feature extraction layers of a neural network with instantaneous neurons to extract meaningful features. The extracted binary feature vectors are then classified using classification layers containing neurons with binary activations. Gradient descent (backpropagation) is used only on the output layer to perform training for classification. Surrogate gradients are proposed to perform backpropagation with binary gradients. The accuracies obtained for MNIST and the balanced EMNIST data set compare favorably with other approaches. The effect of the stochastic gradient descent (SGD) approximations on learning capabilities of our network are also explored. We also studied catastrophic forgetting and its effect on spiking neural networks (SNNs). For the experiments regarding catastrophic forgetting, in the classification sections of the network we use a modified synaptic intelligence that we refer to as cost per synapse metric as a regularizer to immunize the network against catastrophic forgetting in a Single-Incremental-Task scenario (SIT). In catastrophic forgetting experiments, we use MNIST and EMNIST handwritten digits datasets that were divided into five and ten incremental subtasks respectively. We also examine behavior of the spiking neural network and empirically study the effect of various hyperparameters on its learning capabilities using the software tool SPYKEFLOW that we developed. We employ MNIST, EMNIST and NMNIST data sets to produce our results.

scholarly journals Prediction of sweet corn yield depending on cultivation technology parameters by using linear regression and artificial neural network methods

2018 ◽  
Vol 26 (1) ◽  
pp. 11-15 ◽  
Author(s):  
P. V. Lykhovyd
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Linear Regression ◽  
Data Processing ◽  
Field Experiments ◽  
Sweet Corn ◽  
Corn Yield ◽  
Artificial Neural

Artificial neural networks and linear regression are widely used in particularly all branches of science for modeling and prediction. Linear regression is an old data processing tool, and artificial neural networks are a comparatively new one. The goal of the study was to determine whether artificial neural networks are more accurate than linear regression in sweet corn yield prediction. In the study we used a dataset obtained from field experiments on the technological improvement of sweet corn cultivation. The field experiments were conducted during the period from 2014 to 2016 on dark-chestnut soil under drip irrigated conditions in the Steppe Zone of Ukraine. We studied the impact of the moldboard plowing depths, mineral fertilizer application rates and plant densities on the crop yield. A significant impact of all the studied factors on the sweet corn productivity was proved by using the analysis of variance. The highest yield of sweet corn ears without husks (10.93 t ha–1) was under the moldboard plowing at the depth of 20–22 cm, mineral fertilizers application rate of N120P120, plant density of 65,000 plants ha–1. Data processing by using the linear regression and artificial neural network methods showed that the latter is a great deal better than linear regression in sweet corn yield prediction. Higher accuracy of the artificial neural network prediction was proved by the higher value of the coefficient of determination (R2) – 0.978, in comparison to 0.897 for the linear regression prediction model. We conclude that artificial neural networks are a much better data processing tool, especially, in the life sciences and for prediction of the non-linear natural processes and phenomena. The main disadvantage of the neural network models is their “black box” nature. However, linear regression will not lose its popularity among scientists in the nearest future. Linear regression is a much simpler data analysis tool, it is easier to perform the prediction, but it still provides a sufficiently high level of accuracy.

scholarly journals Enhancement of Performance for Steam Turbine in Thermal Power Plants Using Artificial Neural Network and Electric Circuit Design

2018 ◽  
Vol 2018 ◽  
pp. 1-9
Author(s):  
Hosham Salim ◽  
Khalid Faisal ◽  
Raheel Jawad
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Power Plant ◽  
Circuit Design ◽  
Electric Circuit ◽  
Maximum Deviation ◽  
Artificial Neural

Design and implantation of electric circuit for enhanced performance of steam power plant and artificial neural networks technique are used to control turbine. Artificial neural networks technique is used to control a lot of industrial models practically. Artificial neural network has been applied to control the important variables of turbine in AL–Dura power plant in Baghdad such as pressure, temperature, speed, and humidity. In this study Simulink model was applied in MATLAB program (v 2014 a) by using artificial neural network (ANN). The method of controlling model is by using NARMA to generate data and train network. ANN is offline. ANN requires data to obtain results and for comparison with actual power plant. The values of the input variables have a large effect on the number of nodes and epochs and in hidden layer of the artificial neural network they also affect performance of ANN. The electric circuit of sensors consists of transformer, DC bridge, and voltage regulator. Comparing the results from modeling by ANN and electric circuit with experimental data reveals a good agreement and the maximum deviation between the experimental data and predicted results from ANN and circuit design is less than 1%. The novelty in this paper is applying NARMA controller for the purpose of enhancement of turbine performance.

scholarly journals The Budapest Amyloid Predictor and Its Applications

Biomolecules ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 500
Author(s):  
László Keresztes ◽  
Evelin Szögi ◽  
Bálint Varga ◽  
Viktor Farkas ◽  
András Perczel ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Support Vector ◽  
User Needs ◽  
Computational Technique ◽  
Linear Support Vector Machine ◽  
Β Sheets ◽  
Artificial Neural ◽  
Amorphous Aggregation

The amyloid state of proteins is widely studied with relevance to neurology, biochemistry, and biotechnology. In contrast with nearly amorphous aggregation, the amyloid state has a well-defined structure, consisting of parallel and antiparallel β-sheets in a periodically repeated formation. The understanding of the amyloid state is growing with the development of novel molecular imaging tools, like cryogenic electron microscopy. Sequence-based amyloid predictors were developed, mainly using artificial neural networks (ANNs) as the underlying computational technique. From a good neural-network-based predictor, it is a very difficult task to identify the attributes of the input amino acid sequence, which imply the decision of the network. Here, we present a linear Support Vector Machine (SVM)-based predictor for hexapeptides with correctness higher than 84%, i.e., it is at least as good as the best published ANN-based tools. Unlike artificial neural networks, the decisions of the linear SVMs are much easier to analyze and, from a good predictor, we can infer rich biochemical knowledge. In the Budapest Amyloid Predictor webserver the user needs to input a hexapeptide, and the server outputs a prediction for the input plus the 6 × 19 = 114 distance-1 neighbors of the input hexapeptide.

scholarly journals Non-Destructive Micromagnetic Determination of Hardness and Case Hardening Depth Using Linear Regression Analysis and Artificial Neural Networks

Metals ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 18
Author(s):  
Rahel Jedamski ◽  
Jérémy Epp
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Regression Analysis ◽  
Artificial Neural Networks ◽  
Linear Regression ◽  
Linear Regression Analysis ◽  
Case Hardening ◽  
Artificial Neural ◽  
Non Destructive

Non-destructive determination of workpiece properties after heat treatment is of great interest in the context of quality control in production but also for prevention of damage in subsequent grinding process. Micromagnetic methods offer good possibilities, but must first be calibrated with reference analyses on known states. This work compares the accuracy and reliability of different calibration methods for non-destructive evaluation of carburizing depth and surface hardness of carburized steel. Linear regression analysis is used in comparison with new methods based on artificial neural networks. The comparison shows a slight advantage of neural network method and potential for further optimization of both approaches. The quality of the results can be influenced, among others, by the number of teaching steps for the neural network, whereas more teaching steps does not always lead to an improvement of accuracy for conditions not included in the initial calibration.

scholarly journals Optimal Artificial Neural Network Type Selection Method for Usage in Smart House Systems

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 47
Author(s):  
Vasyl Teslyuk ◽  
Artem Kazarian ◽  
Natalia Kryvinska ◽  
Ivan Tsmots
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Input Data ◽  
Optimization Criterion ◽  
Fuzzy Input ◽  
Different Types ◽  
Smart House ◽  
Artificial Neural

In the process of the “smart” house systems work, there is a need to process fuzzy input data. The models based on the artificial neural networks are used to process fuzzy input data from the sensors. However, each artificial neural network has a certain advantage and, with a different accuracy, allows one to process different types of data and generate control signals. To solve this problem, a method of choosing the optimal type of artificial neural network has been proposed. It is based on solving an optimization problem, where the optimization criterion is an error of a certain type of artificial neural network determined to control the corresponding subsystem of a “smart” house. In the process of learning different types of artificial neural networks, the same historical input data are used. The research presents the dependencies between the types of neural networks, the number of inner layers of the artificial neural network, the number of neurons on each inner layer, the error of the settings parameters calculation of the relative expected results.

scholarly journals Improved Effort and Cost Estimation Model Using Artificial Neural Networks and Taguchi Method with Different Activation Functions

Entropy ◽  
2021 ◽  
Vol 23 (7) ◽  
pp. 854
Author(s):  
Nevena Rankovic ◽  
Dragica Rankovic ◽  
Mirjana Ivanovic ◽  
Ljubomir Lazic
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Cost Estimation ◽  
Time Estimation ◽  
Effort Estimation ◽  
Activation Functions ◽  
Estimation Model ◽  
Wide Range ◽  
Software Product ◽  
Artificial Neural

Software estimation involves meeting a huge number of different requirements, such as resource allocation, cost estimation, effort estimation, time estimation, and the changing demands of software product customers. Numerous estimation models try to solve these problems. In our experiment, a clustering method of input values to mitigate the heterogeneous nature of selected projects was used. Additionally, homogeneity of the data was achieved with the fuzzification method, and we proposed two different activation functions inside a hidden layer, during the construction of artificial neural networks (ANNs). In this research, we present an experiment that uses two different architectures of ANNs, based on Taguchi’s orthogonal vector plans, to satisfy the set conditions, with additional methods and criteria for validation of the proposed model, in this approach. The aim of this paper is the comparative analysis of the obtained results of mean magnitude relative error (MMRE) values. At the same time, our goal is also to find a relatively simple architecture that minimizes the error value while covering a wide range of different software projects. For this purpose, six different datasets are divided into four chosen clusters. The obtained results show that the estimation of diverse projects by dividing them into clusters can contribute to an efficient, reliable, and accurate software product assessment. The contribution of this paper is in the discovered solution that enables the execution of a small number of iterations, which reduces the execution time and achieves the minimum error.

Performance Estimation of Direct Methanol Fuel Cell Using Artificial Neural Network

2015 ◽  
Author(s):  
M. A. Rafe Biswas ◽  
Melvin D. Robinson
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Fuel Cell ◽  
Direct Methanol Fuel Cell ◽  
Cell Voltage ◽  
Operating Conditions ◽  
Direct Methanol ◽  
Artificial Neural ◽  
Methanol Fuel Cell

A direct methanol fuel cell can convert chemical energy in the form of a liquid fuel into electrical energy to power devices, while simultaneously operating at low temperatures and producing virtually no greenhouse gases. Since the direct methanol fuel cell performance characteristics are inherently nonlinear and complex, it can be postulated that artificial neural networks represent a marked improvement in performance prediction capabilities. Artificial neural networks have long been used as a tool in predictive modeling. In this work, an artificial neural network is employed to predict the performance of a direct methanol fuel cell under various operating conditions. This work on the experimental analysis of a uniquely designed fuel cell and the computational modeling of a unique algorithm has not been found in prior literature outside of the authors and their affiliations. The fuel cell input variables for the performance analysis consist not only of the methanol concentration, fuel cell temperature, and current density, but also the number of cells and anode flow rate. The addition of the two typically unconventional variables allows for a more distinctive model when compared to prior neural network models. The key performance indicator of our neural network model is the cell voltage, which is an average voltage across the stack and ranges from 0 to 0:8V. Experimental studies were carried out using DMFC stacks custom-fabricated, with a membrane electrode assembly consisting of an additional unique liquid barrier layer to minimize water loss through the cathode side to the atmosphere. To determine the best fit of the model to the experimental cell voltage data, the model is trained using two different second order training algorithms: OWO-Newton and Levenberg-Marquardt (LM). The OWO-Newton algorithm has a topology that is slightly different from the topology of the LM algorithm by the employment of bypass weights. It can be concluded that the application of artificial neural networks can rapidly construct a predictive model of the cell voltage for a wide range of operating conditions with an accuracy of 10−3 to 10−4. The results were comparable with existing literature. The added dimensionality of the number of cells provided insight into scalability where the coefficient of the determination of the results for the two multi-cell stacks using LM algorithm were up to 0:9998. The model was also evaluated with empirical data of a single-cell stack.

scholarly journals Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹

2014 ◽  
Vol 38 (6) ◽  
pp. 1681-1693 ◽  
Author(s):  
Braz Calderano Filho ◽  
Helena Polivanov ◽  
César da Silva Chagas ◽  
Waldir de Carvalho Júnior ◽  
Emílio Velloso Barroso ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Kappa Index ◽  
Class Prediction ◽  
Soil Class ◽  
Serra Do Mar ◽  
The Neural Network ◽  
Artificial Neural ◽  
Local Geology

Soil information is needed for managing the agricultural environment. The aim of this study was to apply artificial neural networks (ANNs) for the prediction of soil classes using orbital remote sensing products, terrain attributes derived from a digital elevation model and local geology information as data sources. This approach to digital soil mapping was evaluated in an area with a high degree of lithologic diversity in the Serra do Mar. The neural network simulator used in this study was JavaNNS and the backpropagation learning algorithm. For soil class prediction, different combinations of the selected discriminant variables were tested: elevation, declivity, aspect, curvature, curvature plan, curvature profile, topographic index, solar radiation, LS topographic factor, local geology information, and clay mineral indices, iron oxides and the normalized difference vegetation index (NDVI) derived from an image of a Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor. With the tested sets, best results were obtained when all discriminant variables were associated with geological information (overall accuracy 93.2 - 95.6 %, Kappa index 0.924 - 0.951, for set 13). Excluding the variable profile curvature (set 12), overall accuracy ranged from 93.9 to 95.4 % and the Kappa index from 0.932 to 0.948. The maps based on the neural network classifier were consistent and similar to conventional soil maps drawn for the study area, although with more spatial details. The results show the potential of ANNs for soil class prediction in mountainous areas with lithological diversity.

Sign in / Sign up

Export Citation Format

Share Document