Fast Learning Neural Network Research Articles

Retracted: Gene Position Index Mutation Detection Algorithm Based on Feedback Fast Learning Neural Network.

[This retracts the article DOI: 10.1155/2021/1716182.].

Fast learning neural network based on texture for Arabic calligraphy identification

<span id="docs-internal-guid-5c723154-7fff-a7b2-3582-b7c2920a9921"><span>Arabic calligraphy is considered a sort of Arabic writing art where letters in Arabic can be written in various curvy or segments styles. The efforts of automating the identification of Arabic calligraphy by using artificial intelligence were less comparing with other languages. Hence, this article proposes using four types of features and a single hidden layer neural network for training on Arabic calligraphy and predicting the type of calligraphy that is used. For neural networks, we compared the case of non-connected input and output layers in extreme learning machine ELM and the case of connected input-output layers in FLN. The prediction accuracy of fast learning machine FLN was superior comparing ELM that showed a variation in the obtained accuracy. </span></span>

Gene Position Index Mutation Detection Algorithm Based on Feedback Fast Learning Neural Network.

In the detection of genome variation, the research on the internal correlation of reference genome is deepening; the detection of variation in genome sequence has become the focus of research, and it has also become an effective path to find new genes and new functional proteins. The targeted sequencing sequence is used to sequence the exon region of a specific gene in cancer gene detection, and the sequencing depth is relatively large. Traditional alignment algorithms will lose some sequences, which will lead to inaccurate mutation detection. This paper proposes a mutation detection algorithm based on feedback fast learning neural network position index. By establishing a position index relationship for ACGT in the DNA sequence, the subsequence is decomposed into the position relationship of different subsequences corresponding to the main sequence. The positional relationship of the subsequence in the main sequence is determined by the positional relationship. Analyzing SNP and InDel mutations, even structural mutations, through the position correlation of sequences has the advantages of high precision and easy implementation by personal computers. The feedback fast learning neural network is used to verify whether there is a linear relationship between two or more positions. Experimental results show that the mutation points detected by position index are more than those detected by Bcftools, Freebye, Vanscan2, and Gatk.

Kinematics model identification and motion control of robot based on fast learning neural network

As a static network, the slow learning of back propagation (BP) neural network is an insurmountable disadvantage facing dynamic system identification. In contrast, dynamic neural network provides a potential choice, representing the development direction of neural network modeling, identification and control. Based on dynamic Elman network, a new learning neural network structure, called fast learning neural network, is proposed in this paper. It not only conforms to the basic characteristics of biological neural network, but also has the advantages of simple algorithm, fast learning convergence and high identification accuracy of linear and non-linear systems. Based on the experimental data, this network is applied to the identification of the motion model of modular robots to obtain the non-linear kinematics model of robots. Therefore, this kind of neural network is very suitable for robot kinematics model identification and motion control. The simulation results show that it is appropriate to identify the kinematics model and control the motion of the robot based on fast learning neural network; and the combination of fast learning and ELM network speeds up the training efficiency.

Energy-Efficient Gabor Kernels in Neural Networks with Genetic Algorithm Training Method

Deep-learning convolutional neural networks (CNNs) have proven to be successful in various cognitive applications with a multilayer structure. The high computational energy and time requirements hinder the practical application of CNNs; hence, the realization of a highly energy-efficient and fast-learning neural network has aroused interest. In this work, we address the computing-resource-saving problem by developing a deep model, termed the Gabor convolutional neural network (Gabor CNN), which incorporates highly expression-efficient Gabor kernels into CNNs. In order to effectively imitate the structural characteristics of traditional weight kernels, we improve upon the traditional Gabor filters, having stronger frequency and orientation representations. In addition, we propose a procedure to train Gabor CNNs, termed the fast training method (FTM). In FTM, we design a new training method based on the multipopulation genetic algorithm (MPGA) and evaluation structure to optimize improved Gabor kernels, but train the rest of the Gabor CNN parameters with back-propagation. The training of improved Gabor kernels with MPGA is much more energy-efficient with less samples and iterations. Simple tasks, like character recognition on the Mixed National Institute of Standards and Technology database (MNIST), traffic sign recognition on the German Traffic Sign Recognition Benchmark (GTSRB), and face detection on the Olivetti Research Laboratory database (ORL), are implemented using LeNet architecture. The experimental result of the Gabor CNN and MPGA training method shows a 17–19% reduction in computational energy and time and an 18–21% reduction in storage requirements with a less than 1% accuracy decrease. We eliminated a significant fraction of the computation-hungry components in the training process by incorporating highly expression-efficient Gabor kernels into CNNs.

Flexible fast learning neural networks and their application for building highly reliable biometric cryptosystems based on dynamic features

Abstract The paper concludes an overview of the most promising methods of pattern recognition (deep learning, convolutional, evolutionary, progressive, shallow, wide, hybrid artificial neural networks etc.) in regard to the possibility of their use to build highly reliable biometric cryptosystems on the basis of dynamic features. The authors propose a new approach - the development and training of flexible neural networks. For its implementation, the mathematical apparatus is developed that uses elements of various types of artificial neural networks, the probability theory, and mathematical statistics. The paper presents the results of these studies and formulates the range of the problems to be solved for creating a perspective fundamentals for building highly reliable biometric cryptosystems

A Fast Learning Neuro Adaptive Control of Buck Converter driven PMDC Motor: Design, Analysis and Validation

This paper presents a novel fast learning neural network for the estimation of load torque in PMDC motor. The control objective of angular velocity trajectory tracking is achieved by designing a controller for cascaded Buck converter PMDC motor system by utilizing an adaptive backstepping methodology augmented with a new Type-II Chebyshev neural network (CNN). The online learning laws for the neural network are developed, satisfying overall closed loop system stability using Lyapunov stability criterion. A rigorous stability analysis has been provided. Performance of the proposed control method is validated on a digital platform using dSPACE Control Desk DS1103 set-up with TM320F240 Digital Signal Processor. The dynamic response of Buck converter driven PMDC motor is examined for settling time, peak undershoot and overshoot guaranteeing the transient performance under conventional adaptive backstepping control and Type-I CNN based adaptive backstepping control techniques. Further, such results are compared with those obtained using the proposed method under start-up, wide range variations in load torque and reference trajectory.

A new pruning method for extreme learning machines via genetic algorithms

Extreme learning machine (ELM) is a recently proposed learning algorithm for single hidden layer feedfoward neural networks (SLFN) that achieved remarkable performances in various applications. In ELM, the hidden neurons are randomly assigned and the output layer weights are learned in a single step using the Moore-Penrose generalized inverse. This approach results in a fast learning neural network algorithm with a single hyperparameter (the number of hidden neurons). Despite the aforementioned advantages, using ELM can result in models with a large number of hidden neurons and this can lead to poor generalization. To overcome this drawback, we propose a novel method to prune hidden layer neurons based on genetic algorithms (GA). The proposed approach, referred as GAP-ELM, selects subset of the hidden neurons to optimize a multiobjective fitness function that defines a compromise between accuracy and the number of pruned neurons. The performance of GAP-ELM is assessed on several real world datasets and compared to other SLFN and a well known pruning method called Optimally Pruned ELM (OP-ELM). On the basis of our experiments, we can state that GAP-ELM is a valid alternative for classification tasks.

Intelligent feature extraction and classification of anuran vocalizations

An intelligent identification system for mixed anuran vocalizations is developed in this work to provide the public to easily consult online. The raw mixed anuran vocalization samples are first filtered by noise removal, high frequency compensation, and discrete wavelet transform techniques in order. An adaptive end-point detection segmentation algorithm is proposed to effectively separate the individual syllables from the noise. Six features, including spectral centroid, signal bandwidth, spectral roll-off, threshold-crossing rate, spectral flatness, and average energy, are extracted and served as the input parameters of the classifier. Meanwhile, a decision tree is constructed based on several parameters obtained during sample collection in order to narrow the scope of identification targets. Then fast learning neural-networks are employed to classify the anuran species based on feature set chosen by wrapper feature selection method. A series of experiments were conducted to measure the outcome performance of the proposed work. Experimental results exhibit that the recognition rate of the proposed identification system can achieve up to 93.4%. The effectiveness of the proposed identification system for anuran vocalizations is thus verified.

Fast learning neural networks using Cartesian genetic programming

A fast learning neuroevolutionary algorithm for both feedforward and recurrent networks is proposed. The method is inspired by the well known and highly effective Cartesian genetic programming (CGP) technique. The proposed method is called the CGP-based Artificial Neural Network (CGPANN). The basic idea is to replace each computational node in CGP with an artificial neuron, thus producing an artificial neural network. The capabilities of CGPANN are tested in two diverse problem domains. Firstly, it has been tested on a standard benchmark control problem: single and double pole for both Markovian and non-Markovian cases. Results demonstrate that the method can generate effective neural architectures in substantially fewer evaluations in comparison to previously published neuroevolutionary techniques. In addition, the evolved networks show improved generalization and robustness in comparison with other techniques. Secondly, we have explored the capabilities of CGPANNs for the diagnosis of Breast Cancer from the FNA (Finite Needle Aspiration) data samples. The results demonstrate that the proposed algorithm gives 99.5% accurate results, thus making it an excellent choice for pattern recognitions in medical diagnosis, owing to its properties of fast learning and accuracy.The power of a CGP based ANN is its representation which leads to an efficient evolutionary search of suitable topologies. This opens new avenues for applying the proposed technique to other linear/non-linear and Markovian/non-Markovian control and pattern recognition problems.

The use of fully polarimetric information for the fuzzy neural classification of SAR images

Presents a method, based on a fuzzy neural network, that uses fully polarimetric information for terrain and land-use classification of synthetic aperture radar (SAR) image. The proposed approach makes use of statistical properties of polarimetric data, and takes advantage of a fuzzy neural network. A distance measure, based on a complex Wishart distribution, is applied using the fuzzy c-means clustering algorithm, and the clustering result is then incorporated into the neural network. Instead of preselecting the polarization channels to form a feature vector, all elements of the polarimetric covariance matrix serve as the target feature vector as inputs to the neural network. It is thus expected that the neural network will include fully polarimetric backscattering information for image classification. With the generalization, adaptation, and other capabilities of the neural network, information contained in the covariance matrix, such as the amplitude, the phase difference, the degree of polarization, etc., can be fully explored. A test image, acquired by the Jet Propulsion Laboratory Airborne SAR (AIRSAR) system, is used to demonstrate the advantages of the proposed method. It is shown that the proposed approach can greatly enhance the adaptability and the flexibility giving fully polarimetric SAR for terrain cover classification. The integration of fuzzy c-means (FCM) and fast generalization dynamic learning neural network (DLNN) capabilities makes the proposed algorithm an attractive and alternative method for polarimetric SAR classification.

A neural network architecture for automatic segmentation of fluorescence micrographs

A system for the automatic segmentation of fluorescence micrographs is presented. In the first step, positions of fluorescent cells are detected by a fast learning neural network, which acquires the visual knowledge from a set of training cell-image patches selected by the user. Guided by the detected cell positions the system extracts in the second step the contours of the cells. For contour extraction, a recurrent neural network model is used to approximate the cell shapes. Even though the micrographs are noisy and the fluorescent cells vary in shape and size, the system detects at minimum 95% of the cells.

A neural network-based intelligent metasearch engine

Determining the relevancy of web pages to a query term is basic to the working of any search engine. In this paper we present a neural network based algorithm to classify the relevancy of search results on a metasearch engine. The fast learning neural network technology used by us enables the metasearch engine to handle a query term in a reasonably short time and return the search results with high accuracy.