The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we present a method for stereo super-resolution which employs a deep network. The network is trained using the residual image so as to obtain a high resolution image from two, low resolution views. Our network is comprised by two deep sub-nets which share, at their output, a single convolutional layer. This last layer in the network delivers an estimate of the residual image which is...
Optimization is important in neural networks to iteratively update weights for pattern classification. Existing optimization techniques suffer from suboptimal local minima and slow convergence rate. In this paper, stochastic diagonal Approximate Greatest Descent (SDAGD) algorithm is proposed to optimize neural network weights using multi-stage backpropagation manner. SDAGD is derived from the operation...
To improve the performance of the convolutional neural networks, it is normally done by increase the deepness or put more layers to the network. By doing such, the number of parameters is increased. In this paper, NU-InNet, which was developed from GoogLeNet, is modified by adding more layers to the network in order to improve the accuracy of the network while keeping the number of the parameters...
The speed of machine learning has been a concern of the people. The speed of Extreme Learning Machine (ELM) has been improved very faster than others. However, the speed of Sequential Extreme Learning Machine is still slow. So, a fast sequence Extreme Learning Machine (Fast Sequential Extreme Learning Machine, FS-ELM) is present by the use of iterative calculation in calculation of the output weights...
Deep convolutional neural networks (DCNN's) have shown great value in approaching highly challenging problems in image classification. Based on the successes of DCNNs in scene classification and object detection and localization it is natural to consider whether they would be effective for much simpler computer vision tasks. Our work involves the application of a DCNN to the relatively simple task...
Domain adaptation (DA) algorithms address the problem of distribution shift between training and testing data. Recent approaches transform data into a shared subspace by minimizing the shift between their marginal distributions. We propose a method to learn a common subspace that will leverage the class conditional distributions of training samples along with reducing the marginal distribution shift...
A method for hybridizing supervised learning with adaptive dynamic programming was developed to increase the speed, quality, and robustness of on-line neural network learning from an imperfect teacher. Reinforcement learning is used to modify and enhance the original supervisory signal before learning occurs. This paper describes the method of hybridization and presents a model problem in which a...
In this paper, convolutional neural networks (CNNs) is employed for remote-sensing scene classification, which fully utilizes the semantic features extracted from the images while ignoring some traditional features. Consider the limited labeled samples, CaffeNet model as the pre-trained architecture is adopted. By fine-tuning the pre-trained models, the proposed method is expected to be robust and...
In this paper, we study how to initialize the convolutional neural network (CNN) model for training on a small dataset. Specially, we try to extract discriminative filters from the pre-trained model for a target task. On the basis of relative entropy and linear reconstruction, two methods, Minimum Entropy Loss (MEL) and Minimum Reconstruction Error (MRE), are proposed. The CNN models initialized by...
Gait as a biometric feature that can be measured remotely without physical contact and proximal sensing has attract significant attention. This paper proposes to use con-volutional neural networks (ConvNets) and multi-task learning model(MLT) to identify human gait and to predict multiple human attributes simultaneously. In comparison to previous approaches, two novelty in our convolutional approach...
This paper briefly discusses the basic principle of artificial neural network. BP network model based on time series has been established through an instance. Training and testing have been done for the network using existing observation data. Compared with the measured value through regression analysis, the effectiveness and accuracy of the network have been proved. It can be a prediction method...
Currently, the optical character recognition (OCR) is applied in many fields such as reading the office letter and to read the serial on parts of industrial. The most manufacturing focus the processing time and accuracy for inspection process. The learning method of the optical character recognition is used a neural network to recognize the fonts and correlation the matching value. The neural network...
In this paper, we tackle the storage and computational cost of linear projections used in dimensionality reduction for near duplicate image retrieval. We propose a new method based on metric learning with a lower training cost than existing methods. Moreover, by adding a sparsity constraint, we obtain a projection matrix with a low storage and projection cost. We carry out experiments on a well known...
Iterative learning control (ILC) algorithms are typically used to iteratively refine the feed-forward control input to a system to achieve an optimized performance objective. Because of its ease of implementation and robustness, ILC has found widespread use in a variety of industrial applications. However, a key limitation of ILC is the requirement that learning has to be re-initiated for each new...
There has been developed many method for the better convergence and generalization ability of neural network. Multilayer Perceptron (MLP) is made multi hidden layered structure for better performance. But in these types of structures still error from any output classes propagates in the backward direction which has a negative impact on the weight updating as well as overall performance because every...
Given n nominal samples, a query point η and a significance level a, the uniformly most powerful test for anomaly detection can be to test p(η) ≤ α, where p(η) is the p-value function of η. In [1] a p-value estimator is proposed which is based on ranking some statistic over all data samples, and is shown to be asymptotically consistent. Relying on this framework we propose a new statistic for p-value...
Multi-threaded applications are commonplace in today's software landscape. Pushing the boundaries of concurrency and parallelism, programmers are maximizing performance demanded by stakeholders. However, multi-threaded programs are challenging to test and debug. Prone to their own set of unique faults, such as race conditions, testers need to turn to automated validation tools for assistance. This...
To solve the problem that it is difficult to construct an exact mathematic model for the electro-hydraulic position servo system of a pump-controlled cylinder with nonlinearity and time-varying property, HHGA-RBFNN is proposed. Each chromosome only contains three parameters including the number of hidden nodes, center and width of radial basis function; so that the complexity of proposed algorithm...
Although particle swam optimization (PSO) algorithm is a good optimization tool for feedforward neural network s(FNN), it is easy to lose the diversity of the swarm and suffer from premature convergence. An improved PSO algorithm based on the attractive and repulsive PSO (ARPSO) is proposed to train FNN in this paper. In addition to the phases of repulsion and attraction, the third phase named as...
In this paper, a faster supervised algorithm (BPfast) for the neural network training is proposed that maximizes the derivative of sigmoid activation function during back-propagation (BP) training. BP adjusts the weights of neural network with minimizing an error function. Due to the presence of derivative information in the weight update rule, BP goes to `premature saturation' that slows down the...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.