Comprehensive Introduction to Neural Networks

Unknowingly, artificial intelligence (AI) has become an inevitable part of our lives. In this chapter, the authors discuss how the neural networks, a sub-part of AI, changed the way we analyse things. In this chapter, the advent of neural networks, inspiration from the human brain, simplification models of biological neuron models are discussed. Later, a detailed overview of various neural network models, their strengths, limitations, applications, and challenges are presented in detail.

Download Full-text

Demand Modelling in Telecommunications

Acta Polytechnica ◽

10.14311/1121 ◽

2009 ◽

Vol 49 (2) ◽

Author(s):

M. Chvalina

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Neural Networks ◽

Network Models ◽

Short Term ◽

Neural Network Models ◽

Term Forecast ◽

Artificial Intelligence Methods ◽

Demand Modelling

This article analyses the existing possibilities for using Standard Statistical Methods and Artificial Intelligence Methods for a short-term forecast and simulation of demand in the field of telecommunications. The most widespread methods are based on Time Series Analysis. Nowadays, approaches based on Artificial Intelligence Methods, including Neural Networks, are booming. Separate approaches will be used in the study of Demand Modelling in Telecommunications, and the results of these models will be compared with actual guaranteed values. Then we will examine the quality of Neural Network models.

Download Full-text

Modified Tartagli Method for Calculation of Jominy Hardenability Curve

Materials Science Forum ◽

10.4028/www.scientific.net/msf.575-578.892 ◽

2008 ◽

Vol 575-578 ◽

pp. 892-897 ◽

Cited By ~ 4

Author(s):

Wojciech Sitek ◽

Jacek Trzaska ◽

Leszek Adam Dobrzański

Keyword(s):

Neural Network ◽

Neural Networks ◽

Chemical Composition ◽

Network Models ◽

Steel Grade ◽

Regression Coefficients ◽

Neural Network Models ◽

The Neural Network ◽

The Neural Networks ◽

Hardenability Curve

Basing on the experimental results of the hardenability investigations, which employed Jominy method, the model of the neural networks was developed and fully verified experimentally. The model makes it possible to obtain Jominy hardenability curves basing on the steel chemical composition. The modified hardenability curves calculation method is presented in the paper, initially developed by Tartaglia, Eldis, and Geissler, later extended by T. Inoue. The method makes use of the similarity of the Jominy curve to the hyperbolic secant function. The empirical formulae proposed by the authors make calculation of the hardenability curve possible basing on the chemical composition of the steel. However, regression coefficients characteristic for the particular steel grade must be known. Replacing some formulae by the neural network models is proposed in the paper.

Download Full-text

Hybrid discrete-time neural networks

Philosophical Transactions of The Royal Society A Mathematical Physical and Engineering Sciences ◽

10.1098/rsta.2010.0171 ◽

2010 ◽

Vol 368 (1930) ◽

pp. 5071-5086 ◽

Cited By ~ 8

Author(s):

Hongjun Cao ◽

Borja Ibarz

Keyword(s):

Neural Network ◽

Neural Networks ◽

Discrete Time ◽

Evolution Equations ◽

Network Models ◽

State Transitions ◽

Phase Plane Analysis ◽

Discrete Time System ◽

Neuron Models ◽

Neural Network Models

Hybrid dynamical systems combine evolution equations with state transitions. When the evolution equations are discrete-time (also called map-based), the result is a hybrid discrete-time system. A class of biological neural network models that has recently received some attention falls within this category: map-based neuron models connected by means of fast threshold modulation (FTM). FTM is a connection scheme that aims to mimic the switching dynamics of a neuron subject to synaptic inputs. The dynamic equations of the neuron adopt different forms according to the state (either firing or not firing) and type (excitatory or inhibitory) of their presynaptic neighbours. Therefore, the mathematical model of one such network is a combination of discrete-time evolution equations with transitions between states, constituting a hybrid discrete-time (map-based) neural network. In this paper, we review previous work within the context of these models, exemplifying useful techniques to analyse them. Typical map-based neuron models are low-dimensional and amenable to phase-plane analysis. In bursting models, fast–slow decomposition can be used to reduce dimensionality further, so that the dynamics of a pair of connected neurons can be easily understood. We also discuss a model that includes electrical synapses in addition to chemical synapses with FTM. Furthermore, we describe how master stability functions can predict the stability of synchronized states in these networks. The main results are extended to larger map-based neural networks.

Download Full-text

A Novel Low-Bit Quantization Strategy for Compressing Deep Neural Networks

Computational Intelligence and Neuroscience ◽

10.1155/2020/7839064 ◽

2020 ◽

Vol 2020 ◽

pp. 1-7

Author(s):

Xin Long ◽

XiangRong Zeng ◽

Zongcheng Ben ◽

Dianle Zhou ◽

Maojun Zhang

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Neural Networks ◽

Computational Cost ◽

Network Models ◽

Memory Consumption ◽

Neural Network Models ◽

The Neural Network ◽

The Neural Networks ◽

Novel Strategy

The increase in sophistication of neural network models in recent years has exponentially expanded memory consumption and computational cost, thereby hindering their applications on ASIC, FPGA, and other mobile devices. Therefore, compressing and accelerating the neural networks are necessary. In this study, we introduce a novel strategy to train low-bit networks with weights and activations quantized by several bits and address two corresponding fundamental issues. One is to approximate activations through low-bit discretization for decreasing network computational cost and dot-product memory. The other is to specify weight quantization and update mechanism for discrete weights to avoid gradient mismatch. With quantized low-bit weights and activations, the costly full-precision operation will be replaced by shift operation. We evaluate the proposed method on common datasets, and results show that this method can dramatically compress the neural network with slight accuracy loss.

Download Full-text

Utilizing Artificial Neural Network for Load Prediction Caused by Fluid Sloshing in Tanks

Geofluids ◽

10.1155/2021/3537542 ◽

2021 ◽

Vol 2021 ◽

pp. 1-17

Author(s):

Hossein Goudarzvand Chegini ◽

Gholamreza Zarepour

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Models ◽

Harmonic Excitation ◽

Load Prediction ◽

Neural Network Models ◽

Fluid Sloshing ◽

Particle Hydrodynamics ◽

Feed Forward Neural Networks ◽

The Neural Networks

In this research, neural network models were used to predict the action of sloshing phenomena in a tank containing fluid under harmonic excitation. A new methodology is proposed in this analysis to test and simulate fluid sloshing behavior in the tank. The sloshing behavior was first modeled using the smooth particle hydrodynamics (SPH) method. The backpropagation of the error algorithm was then used to apply the two multilayer feed-forward neural networks and the recurrent neural network. The findings of the SPH process are employed in the training and testing of neural networks. Input neural network data include the tank position, velocity, and acceleration, neural output data, and fluid sloshing curve wave position. The findings of the neural networks were correlated with the experimental evidence provided in the literature. The findings revealed that neural networks can be used to predict fluid sloshing.

Download Full-text

Influence of the Depth of the Convolutional Neural Networks on an Artificial Intelligence Model for Diagnosis of Orthognathic Surgery

Journal of Personalized Medicine ◽

10.3390/jpm11050356 ◽

2021 ◽

Vol 11 (5) ◽

pp. 356

Author(s):

Ye-Hyun Kim ◽

Jae-Bong Park ◽

Min-Seok Chang ◽

Jae-Jun Ryu ◽

Won Hee Lim ◽

...

Keyword(s):

Artificial Intelligence ◽

Neural Networks ◽

Orthognathic Surgery ◽

Area Under The Curve ◽

Network Models ◽

Neural Network Models ◽

Test Set ◽

The Neural Networks ◽

The Difference ◽

Average Success Rate

The aim of this study was to investigate the relationship between image patterns in cephalometric radiographs and the diagnosis of orthognathic surgery and propose a method to improve the accuracy of predictive models according to the depth of the neural networks. The study included 640 and 320 patients requiring non-surgical and surgical orthodontic treatments, respectively. The data of 150 patients were exclusively classified as a test set. The data of the remaining 810 patients were split into five groups and a five-fold cross-validation was performed. The convolutional neural network models used were ResNet-18, 34, 50, and 101. The number in the model name represents the difference in the depth of the blocks that constitute the model. The accuracy, sensitivity, and specificity of each model were estimated and compared. The average success rate in the test set for the ResNet-18, 34, 50, and 101 was 93.80%, 93.60%, 91.13%, and 91.33%, respectively. In screening, ResNet-18 had the best performance with an area under the curve of 0.979, followed by ResNets-34, 50, and 101 at 0.974, 0.945, and 0.944, respectively. This study suggests the required characteristics of the structure of an artificial intelligence model for decision-making based on medical images.

Download Full-text

APPLICATION OF COMPUTER VISION TECHNOLOGIES FOR THE DEVELOPMENT OF A MODEL FOR THE RECOGNITION OF LESIONS OF CULTIVATED PLANTS

Bulletin of the South Ural State University Ser Computer Technologies Automatic Control & Radioelectronics ◽

10.14529/ctcr210301 ◽

2021 ◽

Vol 21 (3) ◽

pp. 5-13

Author(s):

N.A. Yanishevskaya ◽

◽

I.P. Bolodurina ◽

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Neural Networks ◽

Computer Vision ◽

Network Models ◽

Cultivated Plants ◽

Industrial Complex ◽

Neural Network Models ◽

Crop Disease ◽

The Russian Federation

In the Russian Federation, the agro-industrial complex is one of the leading sectors of the eco-nomy with a volume of domestic product of 4.5%. Russia owns 10 % of all arable land in the world. According to the data on the sown areas by crops in 2020, most of the agricultural area of Russia is occupied by wheat. The Russian Federation ranks third in the ranking of leading countries in the production of this type of grain crops, as well as leading positions in its export. Brown (leaf) and linear (stem) rust is the most harmful disease of grain crops. It is the reason for the sparseness of wheat crops and leads to a sharp decrease in yield. Therefore, one of the main tasks of farmers is to preserve the crop from diseases. The application of such areas of artificial intelligence as computer vision, machine learning and deep learning is able to cope with this task. These artificial intelligence technologies allow us to successfully solve applied problems of the agro-industrial complex using automated analysis of photographic materials. Aim. To consider the application of computer vision methods for the problem of classification of lesions of cultivated plants on the example of wheat. Materials and methods. The CGIAR Computer Vision for Crop Disease dataset for the crop disease recognition task is taken from the open source Kaggle. It is proposed to use an approach to the re-cognition of lesions of cultivated plants using the well-known neural network models ResNet50, DenseNet169, VGG16 and EfficientNet-B0. Neural network models receive images of wheat as in-put. The output of neural networks is the class of plant damage. To overcome the effect of overfit-ting neural networks, various regularization techniques are investigated. Results. The results of the classification quality, estimated by the software using the F1-score metric, which is the average harmonic between the Precision and Recall measures, are presented. Conclusion. As a result of the conducted research, it was found that the DenseNet model showed the best recognition accuracy us-ing a combination of transfer learning technology and DropOut and L2 regulation technologies to overcome the effect of retraining. The use of this approach allowed us to achieve a recognition ac-curacy of 91%.

Download Full-text

ARTIFICIAL NEURAL NETWORKS IN FOREX CURRENCY MARKETS

June-2020 - International Journal of Engineering Sciences & Research Technology ◽

10.29121/ijesrt.v10.i5.2021.10 ◽

2021 ◽

Vol 10 (5) ◽

pp. 89-92

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Neural Networks ◽

Artificial Neural Networks ◽

Human Brain ◽

Daily Life ◽

Currency Markets ◽

Artificial Neurons ◽

The Neural Networks ◽

Artificial Neural

The Artificial Intelligence is growing and covering various aspects of our daily life. The idea seems to be very complex. It seems that a program cannot be developed using our home PC. But believe me, it's not that difficult. Let us try to understand what the neural networks are and how they can be applied in trading. Artificial Neural Networks can be used in forex Currency Trading, for finding or predicting the next possible movements. We know that Artificial Neural Networks involves study of neurons in the human brain, sometimes called as biological network.ANN is based on connections of nodes, units called as artificial nodes or neurons. Neural network is an entity consisting of artificial neurons, among which there is an organized relationship. These relations are similar to a biological brain.

Download Full-text

Detailed Analysis of Top 10 AI- Deep Learning Neural Networks in Intrusion Detection for Internet of Things

10.21203/rs.3.rs-459229/v1 ◽

2021 ◽

Author(s):

Kanimozhi V ◽

T. Prem Jacob

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Neural Networks ◽

Deep Learning ◽

Internet Of Things ◽

Intrusion Detection ◽

Anomaly Detection ◽

Network Models ◽

Learning Models ◽

Neural Network Models

Abstract Although there exist various strategies for IoT Intrusion Detection, this research article sheds light on the aspect of how the application of top 10 Artificial Intelligence - Deep Learning Models can be useful for both supervised and unsupervised learning related to the IoT network traffic data. It pictures the detailed comparative analysis for IoT Anomaly Detection on sensible IoT gadgets that are instrumental in detecting IoT anomalies by the usage of the latest dataset IoT-23. Many strategies are being developed for securing the IoT networks, but still, development can be mandated. IoT security can be improved by the usage of various deep learning methods. This exploration has examined the top 10 deep-learning techniques, as the realistic IoT-23 dataset for improving the security execution of IoT network traffic. We built up various neural network models for identifying 5 kinds of IoT attack classes such as Mirai, Denial of Service (DoS), Scan, Man in the Middle attack (MITM-ARP), and Normal records. These attacks can be detected by using a "softmax" function of multiclass classification in deep-learning neural network models. This research was implemented in the Anaconda3 environment with different packages such as Pandas, NumPy, Scipy, Scikit-learn, TensorFlow 2.2, Matplotlib, and Seaborn. The utilization of AI-deep learning models embraced various domains like healthcare, banking and finance, findings and scientific researches, and the business organizations along with the concepts like the Internet of Things. We found that the top 10 deep-learning models are capable of increasing the accuracy; minimize the loss functions and the execution time for building that specific model. It contributes a major significance to IoT anomaly detection by using emerging technologies Artificial Intelligence and Deep Learning Neural Networks. Hence the alleviation of assaults that happen on an IoT organization will be effective. Among the top 10 neural networks, Convolutional neural networks, Multilayer perceptron, and Generative Adversarial Networks (GANs) output the highest accuracy scores of 0.996317, 0.996157, and 0.995829 with minimized loss function and less time pertain to the execution. This article added to completely grasp the quirks of irregularity identification of IoT anomalies. Henceforth, this research analysis depicts the implementations of the Top 10 AI-deep learning models, which come in handy that assist you to perceive different neural network models and IoT anomaly detection better.

Download Full-text