scholarly journals A New Computational Model for Astrocytes and Their Role in Biologically Realistic Neural Networks

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Zahra Sajedinia ◽  
Sébastien Hélie
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Synaptic Plasticity ◽  
Computational Model ◽  
Bipartite Network ◽  
Presynaptic Neuron ◽  
Tripartite Synapse ◽  
And Performance ◽  
Robust To Noise

Recent studies in neuroscience show that astrocytes alongside neurons participate in modulating synapses. It led to the new concept of “tripartite synapse”, which means that a synapse consists of three parts: presynaptic neuron, postsynaptic neuron, and neighboring astrocytes. However, it is still unclear what role is played by the astrocytes in the tripartite synapse. Detailed biocomputational modeling may help generate testable hypotheses. In this article, we aim to study the role of astrocytes in synaptic plasticity by exploring whether tripartite synapses are capable of improving the performance of a neural network. To achieve this goal, we developed a computational model of astrocytes based on the Izhikevich simple model of neurons. Next, two neural networks were implemented. The first network was only composed of neurons and had standard bipartite synapses. The second network included both neurons and astrocytes and had tripartite synapses. We used reinforcement learning and tested the networks on categorizing random stimuli. The results show that tripartite synapses are able to improve the performance of a neural network and lead to higher accuracy in a classification task. However, the bipartite network was more robust to noise. This research provides computational evidence to begin elucidating the possible beneficial role of astrocytes in synaptic plasticity and performance of a neural network.

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.

scholarly journals Development and Performance Evaluation of a Computer Program Based on Neural Network Mathematical Models for Forecasting By- Product Yield

2020 ◽  
Vol 174 ◽  
pp. 03023
Author(s):  
Yelena Vasileva ◽  
Aleksandr Nevedrov ◽  
Sergey Subbotin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Mathematical Models ◽  
Design Method ◽  
Coal Tar ◽  
Product Yield ◽  
Production Values ◽  
And Performance ◽  
Crude Benzene ◽  
By Products

Process performance of coking plants are based on data on the yield of by-products of coking coal and their quality, therefore, much attention is paid to the issues of their analysis. In view of the complexity and insufficient knowledge of the relationship between these parameters, mathematical modeling of this dependence using neural networks is of great interest. Based on a mathematical analysis of experimental data on the quality indicators of coal, coal concentrates and the by-product yield, neural network mathematical models have been developed to forecast the parameters under study. The neural network is based on the Ward’s network. Based on the results of the research, the application “Intelligent Information System for Forecasting By-product Yield” was created, which implements neural networks [1]. The relative forecasting error for the parameter “coke” is 0.64±0.23%, “coal tar” is 19.53±5.25%, “crude benzene” is 10.02±2.83%, and “coke gas” is 5.11±1.34%. A comparative analysis of the data obtained using the developed design method is carried out, with the simulation results using existing methods, as well as with the production values of by-products yield.

The Cocktail Party Listener

1994 ◽  
Vol 23 (482) ◽  
Author(s):  
A. R. Kian Abolfazlian ◽  
Brian K. Karlsen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computational Model ◽  
Spectral Data ◽  
Spatial Data ◽  
Speaker Identification ◽  
Cocktail Party ◽  
Human Ability

A complex computational model of the human ability to listen to certain signals in preference of others, also called the cocktail party phenomenon, is built on the basis of surveys into the relevant psychological, DSP, and neural network literature. This model is basically binaural and as such it makes use of both spectral data and spatial data in determining which speaker to listen to. The model uses two neural networks for filtering and speaker identification. Results from some experimentation with type and architecture of these networks are presented along with the results of the model. These results indicate that the model has a distinctive ability to focus on a particular speaker of choice.

scholarly journals High-Order Neural Networks are Equivalent to Ordinary Neural Networks

2019 ◽  
Vol 13 (2) ◽  
pp. 228
Author(s):  
Abdel Latif Abu Dalhoum ◽  
Mohammed Al-Rawi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Order ◽  
Classification Problems ◽  
Equivalence Theorems ◽  
Artificial Neural ◽  
And Performance ◽  
Multiplicative Neurons ◽  
New Research ◽  
Computational Systems

Equivalence of computational systems can assist in obtaining abstract systems, and thus enable better understanding of issues related their design and performance. For more than four decades, artificial neural networks have been used in many scientific applications to solve classification problems as well as other problems. Since the time of their introduction, multilayer feedforward neural network referred as Ordinary Neural Network (ONN), that contains only summation activation (Sigma) neurons, and multilayer feedforward High-order Neural Network (HONN), that contains Sigma neurons, and product activation (Pi) neurons, have been treated in the literature as different entities. In this work, we studied whether HONNs are mathematically equivalent to ONNs. We have proved that every HONN could be converted to some equivalent ONN. In most cases, one just needs to modify the neuronal transfer function of the Pi neuron to convert it to a Sigma neuron. The theorems that we have derived clearly show that the original HONN and its corresponding equivalent ONN would give exactly the same output, which means; they can both be used to perform exactly the same functionality. We also derived equivalence theorems for several other non-standard neural networks, for example, recurrent HONNs and HONNs with translated multiplicative neurons. This work rejects the hypothesis that HONNs and ONNs are different entities, a conclusion that might initiate a new research frontier in artificial neural network research.

scholarly journals Practical Aspects of the Design and Use of the Artificial Neural Networks in Materials Engineering

Metals ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 1832
Author(s):  
Wojciech Sitek ◽  
Jacek Trzaska
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Vital Role ◽  
Materials Engineering ◽  
The Neural Network ◽  
Critical Issues ◽  
Artificial Neural ◽  
The Individual

Artificial neural networks are an effective and frequently used modelling method in regression and classification tasks in the area of steels and metal alloys. New publications show examples of the use of artificial neural networks in this area, which appear regularly. The paper presents an overview of these publications. Attention was paid to critical issues related to the design of artificial neural networks. There have been presented our suggestions regarding the individual stages of creating and evaluating neural models. Among other things, attention was paid to the vital role of the dataset, which is used to train and test the neural network and its relationship to the artificial neural network topology. Examples of approaches to designing neural networks by other researchers in this area are presented.

Neural Network Based Transfer Learning of Manipulator Inverse Displacement Analysis

2020 ◽  
Author(s):  
Houcheng Tang ◽  
Leila Notash
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Transfer Learning ◽  
Learning Approach ◽  
Training Process ◽  
Displacement Analysis ◽  
Performance Targets ◽  
The Neural Networks ◽  
Random Initialization ◽  
And Performance

Abstract In this paper, a neural network based transfer learning approach of inverse displacement analysis of robot manipulators is studied. Neural networks with different structures are applied utilizing data from different configurations of a manipulator for training purposes. Then the transfer learning was conducted between manipulators with different geometric layouts. The training is performed on both the neural networks with pretrained initial parameters and the neural networks with random initialization. To investigate the rate of convergence of data fitting comprehensively, different values of performance targets are defined. The computing epochs and performance measures are compared. It is presented that, depending on the structure of neural network, the proposed transfer learning can accelerate the training process and achieve higher accuracy. For different datasets, the transfer learning approach improves their performance differently.

On Developing and Performance Evaluation of Adaptive Second Order Neural Network With GA-Based Training (ASONN-GA) for Financial Time Series Prediction

2018 ◽  
pp. 231-263 ◽  
Author(s):  
Sarat Chandra Nayak ◽  
Bijan Bihari Misra ◽  
Himansu Sekhar Behera
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Financial Time Series ◽  
Single Layer ◽  
Second Order ◽  
Forecasting Accuracy ◽  
Training Time ◽  
Financial Time ◽  
And Performance

Financial time series forecasting has been regarded as a challenging issue because of successful prediction could yield significant profit, hence require an efficient prediction system. Conventional ANN based models are not competent systems. Higher order neural networks have several advantages over traditional neural networks such as stronger approximation, higher fault tolerance capacity and faster convergence. With the aim of achieving improved forecasting accuracy, this article develops and evaluates the performance of an adaptive single layer second order neural network with GA based training (ASONN-GA). The global search ability of GA has been incorporated with the better generalization ability of a second order neural network and the model is found quite capable in handling the uncertainties and nonlinearities associated with the financial time series. The model takes minimal input data and considered the partially optimized weight set from previous training, hence a significant reduction in training time. The efficiency of the model has been evaluated by forecasting one-step-ahead closing prices and exchange rates of five real stock markets and it is revealed that the ASONN-GA model achieves better forecasting accuracy over other state of the art models.

Improving Returns on Stock Investment through Neural Network Selection

2006 ◽  
pp. 152-164 ◽  
Author(s):  
Tong-Seng Quah
Keyword(s):  
Neural Networks ◽  
Conceptual Development ◽  
Bankruptcy Prediction ◽  
Security Market ◽  
Stock Selection ◽  
Financial Variables ◽  
Stock Investment ◽  
And Performance

Artificial neural networks’ (ANNs’) generalization powers have in recent years received admiration of finance researchers and practitioners. Their usage in such areas as bankruptcy prediction, debt-risk assessment, and security-market applications has yielded promising results. With such intensive research and proven ability of the ANN in the area of security-market application and the growing importance of the role of equity securities in Singapore, it has motivated the conceptual development of this work in using the ANN in stock selection. With their proven generalization ability, neural networks are able to infer the characteristics of performing stocks from the historical patterns. The performance of stocks is reflective of the profitability and quality of management of the underlying company. Such information is reflected in financial and technical variables. As such, the ANN is used as a tool to uncover the intricate relationships between the performance of stocks and the related financial and technical variables. Historical data, such as financial variables (inputs) and performance of the stock (output) is used in this ANN application. Experimental results obtained thus far have been very encouraging.

Sign in / Sign up

Export Citation Format

Share Document