scholarly journals On the Role of the Excitation/Inhibition Balance of Homeostatic Artificial Neural Networks

Entropy ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. 1681
Author(s):  
Maximilian Brütt ◽  
Christian Kaernbach
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Intracellular Calcium ◽  
Cell Activity ◽  
Cortical Cell ◽  
Threshold Value ◽  
The Self ◽  
Self Organization ◽  
Wide Range ◽  
Artificial Neural

Homeostatic models of artificial neural networks have been developed to explain the self-organization of a stable dynamical connectivity between the neurons of the net. These models are typically two-population models, with excitatory and inhibitory cells. In these models, connectivity is a means to regulate cell activity, and in consequence, intracellular calcium levels towards a desired target level. The excitation/inhibition (E/I) balance is usually set to 80:20, a value characteristic for cortical cell distributions. We study the behavior of these homeostatic models outside of the physiological range of the E/I balance, and we find a pronounced bifurcation at about the physiological value of this balance. Lower inhibition values lead to sparsely connected networks. At a certain threshold value, the neurons develop a reasonably connected network that can fulfill the homeostasis criteria in a stable way. Beyond the threshold, the behavior of the artificial neural network changes drastically, with failing homeostasis and in consequence with an exploding number of connections. While the exact value of the balance at the bifurcation point is subject to the parameters of the model, the existence of this bifurcation might explain the stability of a certain E/I balance across a wide range of biological neural networks. Assuming that this class of models describes the self-organization of biological network connectivity reasonably realistically, the omnipresent physiological balance might represent a case of self-organized criticality in order to obtain a good connectivity while allowing for a stable intracellular calcium homeostasis.

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.

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.

Knowledge Discovery with Artificial Neural Networks

2011 ◽  
pp. 669-673
Author(s):  
Juan R. Rabuñal Dopico ◽  
Daniel Rivero Cebrian ◽  
Julián Dorado de la Calle ◽  
Nieves Pedreira Souto
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Knowledge Discovery ◽  
Powerful Technique ◽  
Complex Problems ◽  
New Information ◽  
Wide Range ◽  
The World ◽  
Artificial Neural

The world of Data Mining (Cios, Pedrycz & Swiniarrski, 1998) is in constant expansion. New information is obtained from databases thanks to a wide range of techniques, which are all applicable to a determined set of domains and count with a series of advantages and inconveniences. The Artificial Neural Networks (ANNs) technique (Haykin, 1999; McCulloch & Pitts, 1943; Orchad, 1993) allows us to resolve complex problems in many disciplines (classification, clustering, regression, etc.), and presents a series of advantages that convert it into a very powerful technique that is easily adapted to any environment. The main inconvenience of ANNs, however, is that they can not explain what they learn and what reasoning was followed to obtain the outputs. This implies that they can not be used in many environments in which this reasoning is essential.

The significance of relevance trees in the identification of artificial neural networks input vectors

2013 ◽  
Vol 24 (1) ◽  
pp. 27-34
Author(s):  
G. Manuel ◽  
J.H.C. Pretorius
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Statistical Methods ◽  
Demand Forecasting ◽  
Forecast Model ◽  
Optimization Techniques ◽  
Model Parameters ◽  
Wide Range ◽  
Accurate Forecast ◽  
Artificial Neural

In the 1980s a renewed interest in artificial neural networks (ANN) has led to a wide range of applications which included demand forecasting. ANN demand forecasting algorithms were found to be preferable over parametric or also referred to as statistical based techniques. For an ANN demand forecasting algorithm, the demand may be stochastic or deterministic, linear or nonlinear. Comparative studies conducted on the two broad streams of demand forecasting methodologies, namely artificial intelligence methods and statistical methods has revealed that AI methods tend to hide the complexities of correlation analysis. In parametric methods, correlation is found by means of sometimes difficult and rigorous mathematics. Most statistical methods extract and correlate various demand elements which are usually broadly classed into weather and non-weather variables. Several models account for noise and random factors and suggest optimization techniques specific to certain model parameters. However, for an ANN algorithm, the identification of input and output vectors is critical. Predicting the future demand is conducted by observing previous demand values and how underlying factors influence the overall demand. Trend analyses are conducted on these influential variables and a medium and long term forecast model is derived. In order to perform an accurate forecast, the changes in the demand have to be defined in terms of how these input vectors correlate to the final demand. The elements of the input vectors have to be identifiable and quantifiable. This paper proposes a method known as relevance trees to identify critical elements of the input vector. The case study is of a rapid railway operator, namely the Gautrain.

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.

Damage Mechanisms Identification in FRP Using Acoustic Emission and Artificial Neural Networks

2006 ◽  
Vol 514-516 ◽  
pp. 789-793 ◽  
Author(s):  
Rui de Oliveira ◽  
António Torres Marques
Keyword(s):  
Neural Networks ◽  
Acoustic Emission ◽  
Artificial Neural Networks ◽  
Tensile Test ◽  
A Priori ◽  
The Self ◽  
A Priori Knowledge ◽  
Self Organizing Maps ◽  
Damage Mechanisms ◽  
Artificial Neural

In this study is proposed a procedure for damage discrimination based on acoustic emission signals clustering using artificial neural networks. An unsupervised methodology based on the self-organizing maps of Kohonen is developed considering the lack of a priori knowledge of the different signal classes. The methodology is described and applied to a cross-ply glassfibre/ polyester laminate submitted to a tensile test. In this case, six different AE waveforms were identified. The damage sequence could so be identified from the modal nature of those waves.

scholarly journals Application of Neural Networks in the Tests of Hand Grenade Fuses

2019 ◽  
Vol 68 (1) ◽  
pp. 197-212
Author(s):  
Dariusz Ampuła
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Diagnostic Tests ◽  
Evaluation Method ◽  
Empirical Test ◽  
Evaluation Process ◽  
Test Results ◽  
Linear Character ◽  
Wide Range ◽  
Artificial Neural

The neural networks, which find currently use in the unusually wide range of problems, in such fields as: finance, medicine, geology or physics, were characterized in the article. It was accent, that neural networks are very sophisticated technique of modelling, able to map extremely complex functions. It was noticed particularly, that neural networks had a non-linear character, what very essentially improve the possibilities of their applications. Some previous applications of neural networks were introduced, both in the area of domestic and foreign, including also military applications. The fuse of UZRGM type (Universal Modernized Fuse of Hand Grenades) was characterized, describing his building and way of action, special attention-getting on the tested features during laboratory diagnostic tests. Necessary technical parameters for the first and the second laboratory diagnostic tests, whose purpose was to build two independent neural networks, on the basis of existing test results and undertaken post-diagnostic decisions were designed. A few artificial neural networks were made and finally the best two independent neural networks were chosen. The main parameters of the chosen active neural networks were introduced in the pictures. Concise information, relating to the built artificial neural networks, for the first and the second laboratory diagnostic tests of the fuses of UZRGM type, was presented in the end of the article. In the summary, clearly distinguished are advantages of the applications of the proposed evaluation method, which significantly shortens an evaluation process of new empirical test results and causes complex automatization of an evaluation process of the tested fuses. Keywords: artificial intelligence, neural networks, activation function, hidden neurons, fuse.

Detecting heavy metal contamination in soil using complex permittivity and artificial neural networks

2004 ◽  
Vol 41 (6) ◽  
pp. 1054-1067 ◽  
Author(s):  
J Q Shang ◽  
W Ding ◽  
R K Rowe ◽  
L Josic
Keyword(s):  
Heavy Metals ◽  
Neural Networks ◽  
Heavy Metal ◽  
Artificial Neural Networks ◽  
Complex Permittivity ◽  
Heavy Metal Contamination ◽  
Zinc Salt ◽  
Ann Model ◽  
Wide Range ◽  
Artificial Neural

The use of the complex permittivity, an intrinsic electrical property of materials, to detect the presence and type of heavy metals in soil is investigated. The soil specimens are prepared by mixing the soil with distilled and deionized water, NaCl solutions, and copper and zinc salt solutions and compacting at known water contents. The complex permittivities of the soil specimens are measured in the laboratory using a custom-developed apparatus. A database, which includes both contaminated and uncontaminated soil specimens, is developed, with the soil water content, density, and pore-fluid salinity varying over a relatively wide range. Two artificial neural network (ANN) models are developed to (i) identify whether the heavy metals are present in the soil; and, if so, (ii) distinguish the metal type, based on the complex permittivities measured on the soil specimens. The first ANN model (identification) can correctly identify the presence of heavy metals in 90% of cases. The second ANN model (classification) can correctly classify the type of the heavy metal in 95% of cases. Better performance can be achieved if more complex permittivity data are available for the training of the networks.Key words: heavy metals, soil contamination, contamination detection, complex permittivity, artificial neural networks.

Petroleum Pipeline Leakage Forecasting Based on Artificial Neural Networks

2011 ◽  
Vol 219-220 ◽  
pp. 1003-1007
Author(s):  
Xin Bo Zhang ◽  
Jin Sai Chen
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Complete Information ◽  
Self Organization ◽  
Neural Cells ◽  
Nonlinear Functions ◽  
Forecasting Performance ◽  
Self Adaptation ◽  
Artificial Neural ◽  
Self Learning

The technologies of artificial neural networks can be used to complete information processing of the networks through the interaction of neural cells. The mappings of the stimuli effects and the input and output estimates are obtained via combinations of nonlinear functions. This offers the advantages of self-learning, self-organization, self-adaptation and fault tolerance. It also has the possibility of use in applications for petroleum pipeline leakage forecasting. First we use the flow of the inlet in the pipe as input, and the flow of the outlet in the pipe as output to build a artificial neural network for diagnosing the pipe. This method has been shown to offer better results in performance and efficiency. It is expected that the application of this system will increase sensitivity and further increase petroleum pipeline leakage forecasting performance.

Sign in / Sign up

Export Citation Format

Share Document