Tidbits on Neural Network Training

The purpose of the research, the results of which are presented in this article, is to determine the possibility and evaluate the effectiveness of using a trained neural network in the diagnosis of ringworm. The article provides an analysis of the methods used for diagnosing dermatomycosis in veterinary practice. One of the actively developing areas at present is the use of artificial neural networks in the diagnosis of animal diseases. The authors have developed a method for diagnosing dermatophytosis using a trained neural network. To identify hair damaged by dermatophyte spores in cats, a trained artificial neural network YOLO v5 was used, based on the YOLO architecture (high-precision artificial neural network), which provides high accuracy and speed of object detection in images. Diagnostics was carried out in three stages. The first stage: the diagnosis of hair in cats damaged by dermatophyte spores was carried out using a trained artificial neural network. The second stage: microscopy by a veterinary specialist of the veterinary center. The third stage: comparison of the received data from the trained artificial neural network and veterinary specialists. Three comparative experiments were carried out on 20 depersonalized samples with different ratios from healthy and sick animals. As a result of testing the trichoscopy method using artificial neural networks for diagnosing spore-damaged hair dermatitis in cats, it was found that a trained artificial neural network of 60 studied samples diagnosed dermatophyte spore damage in 20 samples, a veterinarian - in 17. All positive results were confirmed by a mycological laboratory study. and identification of the pathogen. It has been established that the use of a trained artificial neural network increases the diagnostic efficiency by 15% and reduces the time to perform diagnostic microscopy by 60.3%. The application of the proposed method allows to reduce the time of microscopic examination, improve the accuracy of interpretation of the results, automate methods for identifying causative agents of ringworm in small animals and take timely measures to treat the animal.

Logarithm-approximate floating-point multiplier is applicable to power-efficient neural network training

The accurate of i identificationntrinsically disordered proteins or protein regions is of great importance, as they are involved in critical biological process and related to various human diseases. In this paper, we develop a deep neural network that is based on the well-known VGG16. Our deep neural network is then trained through using 1450 proteins from the dataset DIS1616 and the trained neural network is tested on the remaining 166 proteins. Our trained neural network is also tested on the blind test set R80 and MXD494 to further demonstrate the performance of our model. The MCC value of our trained deep neural network is 0.5132 on the test set DIS166, 0.5270 on the blind test set R80 and 0.4577 on the blind test set MXD494. All of these MCC values of our trained deep neural network exceed the corresponding values of existing prediction methods.

Artificial neural networks (ANN) have been widely used in the field of data classification. Normally, training of neural network is applied with the traditional back propagation technique. As, this approach has various drawbacks, training of neural network is done with Particle Swarm Optimization (PSO). PSO has been widely used to solve the diverse kind of optimization problems. Population initialization performs a significant role in meta-heuristic algorithms. This paper describes a new initialization population approach Log Logistic termed as PSOLL-NN to create the initialization of the swarm. The proposed algorithm has been tested for weight optimization of feed forward neural network; and compared with back propagation Algorithm (BPA), standard PSO (PSO-NN), PSO initialized with Halton Sequence (PSOH-NN), Torus sequence (PSOT-NN) and Sobol sequence (PSOS-NN). The experimental results show that the proposed technique performed exceptionally better than the other traditional techniques. Moreover, the outcome of our work presents a foresight that how the proposed initialization technique can be used as an efficient alternative to standard training approaches for the data classification problems.

Approaches presented today in the scientific literature suggest that there are no methodological solutions based on the training of artificial neural networks to predict the direction of industrial development, taking into account a set of factors—innovation, environmental friendliness, modernization and production growth. The aim of the study is to develop a predictive model of performance management of innovative industrial systems by building neural networks. The research methods were correlation analysis, training of neural networks (species—regression), extrapolation, and exponential smoothing. As a result of the research, the estimation efficiency technique of an innovative industrial system in a complex considering the criteria of technical modernization, development, innovative activity, and ecologization is developed; the prognostic neural network models allow to optimize the contribution of signs to the formation of target (set) values of indicators of efficiency for macro and micro-industrial systems that will allow to level a growth trajectory of industrial systems; the priority directions of their development are offered. The following conclusions: the efficiency of industrial systems is determined by the volume of sales of goods, innovative products and waste recycling, which allows to save resources; the results of forecasting depend significantly on the DataSet formulated. Although multilayer neural networks independently select important features, it is advisable to conduct a correlation analysis beforehand, which will provide a higher probability of building a high-quality predictive model. The novelty of the research lies in the development and testing of a unique methodology to assess the effectiveness of industrial systems: it is based on a multidimensional system approach (takes into account factors of innovation, environmental friendliness, modernization and production growth); it combines a number of methodological tools (correlation, ranking and weighting); it expands the method of effectiveness assessment in terms of the composition of variables (previously presented approaches are limited to the aspects considered).

Surface deflection is a phenomenon that causes fine wrinkles on the outer surfaces of sheet metal and deteriorates product external appearance. It is quantitatively defined as the difference between the section curve of the sheet and the ideal curve. In this study, using neural networks, a prediction model for surface deflection according to material properties was constructed and combined with a genetic algorithm; the combination of the material properties was studied to predict the minimum surface deflection. Because of the limited number of simulation data, neural networks were developed using several sampling methods such as central composite design, Latin hypercube sampling, and random sampling. In the training of the neural networks, the optimal hyper-parameter of the neural network was found automatically using Latin hypercube sampling. In conclusion, for prediction of surface deflection in rectangular embossing, neural networks made by central composite design showed the best performance. In addition, it was confirmed that the procedure of combining automatic training of a neural network and the genetic algorithm accurately predicted the set of material properties that generates the minimum surface deflection. Also, the quantity of surface deflection predicted by the neural network was very close to that predicted by finite element analysis.

In present paper, concrete compressive strength is evaluated using back propagation feed-forward artificial neural network. Training of neural network is performed using Levenberg-Marquardt learning algorithm for four architectures of artificial neural networks, one, three, eight and twelve nodes in a hidden layer in order to avoid the occurrence of overfitting. Training, validation and testing of neural network is conducted for 75 concrete samples with distinct w/c ratio and amount of superplasticizer of melamine type. These specimens were exposed to different number of freeze/thaw cycles and their compressive strength was determined after 7, 20 and 32 days. The obtained results indicate that neural network with one hidden layer and twelve hidden nodes gives reasonable prediction accuracy in comparison to experimental results (R=0.965, MSE=0.005). These results of the performed analysis are further confirmed by calculating the standard statistical errors: the chosen architecture of neural network shows the smallest value of mean absolute percentage error (MAPE=, variance absolute relative error (VARE) and median absolute error (MEDAE), and the highest value of variance accounted for (VAF).

Proposes a fuzzy neural expert system (FNES) which has a feedforward fuzzy neural network whose input layer consists of fuzzy cell groups and crisp (non-fuzzy) cell groups. Here, the truthfulness of fuzzy information and crisp information of training data is represented by fuzzy cell groups and crisp cell groups, respectively. The expert system has the following two functions: generalization of the information derived from the training data and embodiment of knowledge in the form of the fuzzy neural network; and extraction of fuzzy If-Then rules with linguistic relative importance of each proposition in an antecedent (If-part) from a trained fuzzy neural network. The paper also gives a method to extract automatically fuzzy If-Then rules from the trained neural network. To prove the effectiveness and validity of the proposed fuzzy neural expert system, a fuzzy neural expert system for medical diagnosis has been developed. >

The training of neural networks (NNs) is a computationally intensive task requiring significant time and resources. This article presents a novel approach to NN training using adiabatic quantum computing (AQC), a paradigm that leverages the principles of adiabatic evolution to solve optimization problems. We propose a universal AQC method that can be implemented on gate quantum computers, allowing for a broad range of Hamiltonians and thus enabling the training of expressive neural networks. We apply this approach to various neural networks with continuous, discrete, and binary weights. The study results indicate that AQC can very efficiently evaluate the global minimum of the loss function, offering a promising alternative to classical training methods.

In a bid to predict the propagation loss of electromagnetic signals, different models based on empirical and deterministic formulas have been used. In this study, different artificial neural network models which are very effective for prediction were used for the prediction of signal power loss in a microcell environment, Obio-Akpor, Port Harcourt, Nigeria. The signal power loss of the area is studied based on three artificial neural network algorithms with nine training functions. For the training of the artificial neural network, the input data were the distance from the transmitter and the signal power loss. Training of neural network is a demanding task in the field of supervised learning research. This is because the main difficulty in adopting artificial neural network is in finding the most suitable combination of learning and training functions for the prediction task. We compared the performance of three training algorithms in feedforward back propagation multi layer perceptron neural network. Nine training functions under three training algorithms were selected: the Gradient descent based algorithms, the Conjugate gradient based algorithms and the Quasi-Newton based algorithms. The work compared the training algorithms on the basis of mean square error, mean absolute error, standard deviation, correlation coefficient, regression on training and validation and the rate of convergence. The general performance of the training functions demonstrates their effectiveness to yield accurate results in short time. The conclusion on the training functions is based on the simulation results using measurement data from the micro environment.

Comparing performances of backpropagation and genetic algorithms in the data classification

Reliable classification using neural networks: a genetic algorithm and backpropagation comparison

This paper presents a new technique for automatically creating analog circuit models. The method extracts piecewise linear models from trained neural networks. A model is a set of linear dependencies between circuit performances and design parameters. The paper illustrates the technique for an OTA circuit - an amplifier circuit widely used in filters and A/D converters for which models for gain and bandwidth were automatically generated. As experiments show, the obtained models have simple form that accurately fits the sampled points and the behavior of the trained neural networks. These models are useful for fast simulation of systems with non-linear behavior and performances.

Training of a neural network is easier than it goes deeper. Deeper architecture makes neural networks more difficult to train because of vanishing gradient and complexity problems, and via this training, deeper neural networks become much time taking and high utilization of computer resources. Introducing residual blocks in neural networks train specifically deeper architecture networks than those used previously. Residual networks gain this achievement by attaching a trip connection to the layers of artificial neural networks. This paper is about showing residual networks and how they work like formulas, we will see residual networks obtain good accuracy, and as well as the model is easier to optimize because Res Net makes training of large structured neural networks more efficient. We will check residual nets on the Image Net dataset with a depth of 152 layers which is 8x more intense than VGG nets yet very less complex. After building this architecture of residual nets gets error up to 3.57% on the Image Net test dataset. We also compare the Res Net result to its equivalent Convolutional Network without residual connection. Our results show that ResNet provides higher accuracy but apart from that, it is more prone to over fitting. Stochastic augmentation of training datasets and adding dropout layers in networks are some of the over fitting prevention methods.

Training of Artificial Neural Networks in a Distributed Environment is considered and applied to a typical example in High Energy Physics interactive analysis. Promising results showing a reduction of the wait time from 5 hours to 5 minutes obtained in a local cluster with 64 nodes are described. Preliminary tests in a wide area network studying the impact of latency time are described; and the future work for integration in a GRID framework, that will be carried in the CrossGrid European Project, is outlined.KeywordsHiggs BosonHigh Energy PhysicsLocal ClusterMaster NodeStandard Model Higgs BosonThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.