Fast Image Classification Algorithms Based on Random Weights Networks

A fast and robust algorithm for training feedforward neural networks (FNNs) by using a variable forgetting factor and U-D factorization-based recursive prediction error (RPE) method is proposed. In comparison with the backpropagation (BP) and RPE based learning algorithms, the proposed algorithm, called UD-RPE, can provide much more accurate learning results in fewer iterations with fewer hidden nodes and improve convergence rate and numerical stability (robustness). In addition, it is less sensitive to start-up parameters, such as initial weights and initial covariance matrix, and the randomness in the observed data. It also has good generalization ability and needs less learning time. Simulation results of nonlinear dynamic system modeling and identification show that the algorithm proposed here is an effective and efficient learning algorithm for FNNs.

In order to solve the problem that the traditional long-term high-speed traffic forecasting algorithm is affected by the approximation ability of the function and easy to fall into the local mass value, we wrote a multivariate-based highway traffic forecasting algorithm scaling and convolutional networks. Because the feedforward wavelet neural network algorithm predicts the short-term traffic flow in different areas, it is necessary to examine the ability to predict the difference between different models. From the standard feedforward wavelet neural network algorithm using global optimization capabilities, we improve the wolf pack algorithm, improve the search accuracy of the algorithm, get the best solution of the estimated value of the work according to the search results when completing the research objectives, and get the ability to predict the work of the model. Feedforward neural network algorithm: we develop and obtain the best short-term high-speed traffic forecast values. The results are as follows: after using the author’s algorithm, the processing time increases by 1.5 seconds, but the average percentage of errors decreases by more than 50%, in fact the error and the root mean square error decreased by about 30%, and the smoothing coefficient increased by about 1%. The prediction of the author’s algorithm for short-term high-speed traffic is better than the wavelet neural network prediction algorithm, and the prediction accuracy and stability of the author’s algorithm are higher.

In this paper a general class of fast learning algorithms for feedforward neural networks is introduced and described. The approach exploits the separability of each layer into linear and nonlinear blocks and consists of two steps. The first step is the descent of the error functional in the space of the outputs of the linear blocks (descent in the neuron space), which can be performed using any preferred optimization strategy. In the second step, each linear block is optimized separately by using a least squares (LS) criterion. To demonstrate the effectiveness of the new approach, a detailed treatment of a gradient descent in the neuron space is conducted. The main properties of this approach are the higher speed of convergence with respect to methods that employ an ordinary gradient descent in the weight space backpropagation (BP), better numerical conditioning, and lower computational cost compared to techniques based on the Hessian matrix. The numerical stability is assured by the use of robust LS linear system solvers, operating directly on the input data of each layer. Experimental results obtained in three problems are described, which confirm the effectiveness of the new method.

The convergence of a class of stochastic pseudo-gradient algorithms driven by correlated data sequences is considered in this paper. The obtained results are applied to a learning algorithm for feedforward neural networks and sufficient conditions for its convergence are determined.

A comparison was carried out of several learning algorithms for training feedforward neural networks with linear threshold units. These learning algorithms do not require an a priori network architecture, but add neurons at will during training. The performance of these algorithms was compared by using training sets with a particular correlation of the input patterns over the full range of possible correlations. For binary input patterns we present a fast method for the selection of input patterns that can be identified by a single neuron. This method is not based on the perceptron learning rule.

Image classification has gained an important role in many applications (landscape planning or assessment, meteorology, biodiversity, etc...). This operation aims to separate different regions of an image having various properties in different classes. In this paper, a back-propagation clustering network is proposed for efficient image classification. Our goal is to be able to determine with accuracy some (ROI) regions of interest in a gray level image. To this end, we introduce a new approach that optimizes network performance and improve its learning using genetic algorithms (GA). GAs are applied to optimize internal parameters of the network structure (weights and bias) through a fitness function. The proposed approach generates classification results with high accuracy and reliability. A comparison study is conducted and proved that the combination between a feed forward neural network and genetic algorithm generates better results than other recent methods in the literature based only on neural network trained with backpropagation algorithm.

In this paper, a facial pose estimation based on synergetic computer approach is introduced. Previous researches have proven that basic synergetic computer is not sufficient to support advanced tasks, especially in the field of facial pose estimation problem, which require more than one pattern to be combined into a single class. In this work, we first investigate one of the extensions of basic synergetic computer, SC-MELT. Original SC-MELT exhibits overfitting phenomenon due to its inverse matrix method used which may deteriorate the classification performance. Moreover, its inflexibility for tuning the “melting level” necessitates modification. For this reason, we applied the notion of MPOD penalty function to modify the original SC-MELT and it yielded Modified SC-MELT. We have applied these techniques to model each facial pose cluster into a view-based adjoint prototype. Thus, a query image is projected to each adjoint prototype to compute the responses for facial pose estimation. Experimental results demonstrate that Modified SC-MELT presents considerable improvement in classification rate as compared to original SC-MELT.

Although cognitive diagnostic models (CDMs) can be useful in the analysis and interpretation of existing tests, little has been developed to specify how one might construct a good test using aspects of the CDMs. This article discusses the derivation of a general CDM index based on Kullback-Leibler information that will serve as a measure of how informative an item is for the classification of examinees. The effectiveness of the index is examined for items calibrated using the deterministic input noisy “and” gate model (DINA) and the reparameterized unified model (RUM) by implementing a simple heuristic to construct a test from an item bank. When compared to randomly constructed tests from the same item bank, the heuristic shows significant improvement in classification rates.

A Logical Neural Network based Character Recognition System that Adapts to an Author's Writing Style

A new fast learning algorithm for a multilayer feedforward neural network is presented. The new algorithm, based on an innovative variable step size and gradient averaging, has excellent properties to overcome major drawbacks of the backpropagation algorithm and shows high convergence speed. The improved performance of the new algorithm in comparison with other algorithms is verified via computer simulations.

In recent years, content-based image retrieval method has attracted the attention of many researchers. With the emergence of large-scale computer vision data set, large-scale image classification is going to become an important challenge in the field of computer vision. The existing image classification algorithms mainly have the following defects: (1) lack of sufficient theoretical basis; (2) lower classification accuracy and larger error; (3) algorithm running time is too long because of large amount of data. In order to solve these problems, we introduce an algorithm based on visual saliency and feature extraction theory. Visual saliency means that intelligent algorithm can mark the significant areas in the picture through the simulation of human visual characteristics, and we can preliminarily screen the large-scale date set in terms of saliency extraction, in order to constitute an initial categories set. Image classification mainly includes three processes, that are feature extraction, computation of image pattern vector, classification. Feature extraction is the key factor that affects the performance of image classification. Comparing to global features of image with blur background, partial occlusion, and illumination changes, local features are mode adaptive. Traditional image classification algorithms only use single feature, thus these methods bring limitations. In this paper, we have a thorough research of image classification methods based on feature combination, and we also propose an algorithm based on multiple feature. At the same time, in order to solve the problem that traditional methods dealing with the whole image in a non-hierarchical way, we introduce the theory of visual saliency detection. The results obviously shows that efficient feature extraction combined with the theory of visual saliency are significant to image classification.

Investigates linear separability in feature space from Tietze extension theorem and function approximation theory, and kernel technique is motivated theoretically. Two kernel-based algorithms are presented. One of them is a general learning algorithm for feedforward neural networks, and they can solve large-scale classification problems.

Linear programming algorithm for neural networks

In this paper, the terminal attractor based back propagation learning algorithms for feedforward neural networks are examined. Through a rigorous mathematical analysis, a condition to guarantee the convergence of the algorithms is given. A simulation study is presented to demonstrate the effectiveness of the analysis.

A fast and robust learning algorithm for feedforward neural networks