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, a novel scheme for online, sparsity-aware learning is presented. A new theory is developed that allows for the incorporation, in a unifying way, of different thresholding rules to promote sparsity, that may even be of a nonconvex nature. The complexity of the algorithm exhibits a linear dependence on the number of free parameters.
Least Squares Support Vector Machine (LS-SVM) is a classic algorithm for regression estimation and classification. But unfortunately, for really large problems, LS-SVM can become highly memory and time consuming. In this paper, we present a simplified algorithm for LS-SVM, called ILS-SVM, which effectively reduces the algorithmic complexity. In order to improve the rate of convergence and overcome...
Traditional gradient-based training algorithms have been known to suffer from local minima and have heavy computation load for obtaining the derivative information. The particle swarm optimization (PSO) method was used as a training algorithm of neural networks to improve the convergence rate. However, as the network architecture grows, the size of swarm increases exponentially, which increase the...
Several object categorization algorithms use kernel methods over multiple cues, as they offer a principled approach to combine multiple cues, and to obtain state-of-the-art performance. A general drawback of these strategies is the high computational cost during training, that prevents their application to large-scale problems. They also do not provide theoretical guarantees on their convergence rate...
This paper suggests to use a block MAP-LMS (BMAP-LMS) adaptive filter instead of an adaptive filter called MAP-LMS for estimating the sparse channels. Moreover to faster convergence than MAP-LMS, this block-based adaptive filter enables us to use a compressed sensing version of it which exploits the sparsity of the channel outputs to reduce the sampling rate of the received signal and to alleviate...
We discuss the role of random basis function approximators in modeling and control. We analyze the published work on random basis function approximators and demonstrate that their favorable error rate of convergence O(1/n) is guaranteed only with very substantial computational resources. We also discuss implications of our analysis for applications of neural networks in modeling and control.
Aiming at the problem in facial feature location, the Active Shape Models algorithm has no evaluable criterion to judge its convergence, and tend to run into local minimum when using the fixed search scale, and how to choose the scale is always an issue. This paper presents a method based on the whole shape gray grads to evaluate the search effects, and an improved search policy of multiscale. The...
To achieve low Bit Error Rate (BER) communication a new fast adaptive equalization technique in Decision Directed (DD) mode is proposed in this paper. The output of the equalizer is quantized to get the desired update signal and a new error term is defined based on a probabilistic scheme. The main feature of this technique is that it achieves low BER comparable to turbo equalizer with less computational...
According to the character of codebook size and codeword dimension in low delay speech coding algorithm, a codebook design algorithm based on modified self-organizing feature map (SOFM) neural network is put forward. The input vectors and weight vectors are normalized. In order to reduce the computation complexity and improve the codebook performance, decompose the adaptive adjusting process of network...
Recently, progressive border sampling (PBS) was proposed for sample selection in supervised learning by progressively learning an augmented full border from small labeled datasets. However, this quadratic learning algorithm is inapplicable to large datasets. In this paper, we incorporate the PBS to a state of the art technique called coupling Markov chain Monte Carlo (CMCMC) in an attempt to scale...
The design of a Chebyshev functional link artificial neural networks (CFLANN) based channel equalizer in digital communication systems is discussed in this paper. The design has been successfully applied to digital communication systems in which 16-QAM modulated signals are transmitted. To improve equalizer performance, a decision feedback mechanism is used in the networks (DF-CFLANN). But the computational...
There are situations of many results and many reasons in the fault diagnosis. The training method of former neural network is supervised by teachers only could forecast or diagnose what kind of failure has occurred to the failure that possibly occurs. As a result of equipment's complexity, it is difficult to find the source of fault accurately and rapidly in practical application even if we know the...
High speed security and defense applications demand a quick decision for face recognition which requires a computationally time-efficient algorithm. These algorithms are primarily used to generate egien values. The generation of eigen values by employing decomposition method normally provides solution in O(n3) time whereas an orthogonalizational process, called fast principal component analysis (PCA)...
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.