Audio signal recovery is a common problem in digital audio restoration field, because of corrupted samples that must be replaced. In this paper a subbands architecture is presented for audio signal recovery, using neural nonlinear prediction based on adaptive spline neural networks. The experimental results show the mean square reconstruction error, and maximum error obtained with increasing ga...

Signals sparse in a transformation domain can be recovered from a reduced set of randomly positioned samples by using compressive sensing algorithms. Simple reconstruction algorithms are presented in the first part of the paper. The missing samples manifest themselves as a noise in this reconstruction. Once the reconstruction conditions for a sparse signal are met and the reconstruction is achi...

We propose an approach for performing adaptive principal component extraction. By this approach, the Least Mean Squared Error Reconstruction (LMSER) Principle is implemented in a successive way such that the reconstruction error is fedback as inputs for training the network's weights. Simulations results have shown that this type of LMSER implementation can perform Robust Principal Component An...

This report deals with multigrid approximations of surfaces. Surface area and volume approximations are discussed for regular grids (3D objects), and surface reconstruction for irregular grids (terrain surfaces). Convergence analysis and approximation error calculations are emphasized. 1 CITR, Tamaki Campus, University Of Auckland, Auckland, New Zealand Multigrid convergence of surface approxim...

Reconstruction error bounds in compressed sensing under Gaussian or uniform bounded noise do not translate easily to the case of Poisson noise. Reasons for this include the signal dependent nature of Poisson noise, and also the fact that the negative log likelihood in case of a Poisson distribution (which is directly related to the generalized Kullback-Leibler divergence) is not a metric and do...

This paper presents an analysis of patterns of error in the triangulation of 3D points from stereo camera systems that are used in field work to study the behavior of bats in flight. A measure of the error present in a 3D reconstruction is proposed. A method for empirically testing the performance of a particular stereo camera configuration through a software simulation is presented. Randomly g...

Non-negative matrix factorization (NMF) is a dimensionality reduction method that usually leads to a part-based representation, and it is shown to be effective for source separation. However, the performance of the source separation degrades when one signal can be described with the bases for the other source signals. In this paper, we propose a discriminative NMF (DNMF) algorithm which exploit...

The fast digital shearlet transform (FDST) was recently introduced as a means to analyze natural images efficiently, owing to the fact that those are typically governed by cartoon-like structures. In this paper, we introduce and discuss a first-order hybrid sigma-delta quantization algorithm for coarsely quantizing the shearlet coefficients generated by the FDST. Radial oversampling in the freq...

Restricted Boltzmann Machines (RBMs) are general unsupervised learning devices to ascertain generative models of data distributions. RBMs are often trained using the Contrastive Divergence learning algorithm (CD), an approximation to the gradient of the data log-likelihood. A simple reconstruction error is often used to decide whether the approximation provided by the CD algorithm is good enoug...