Using an ensemble of classifiers instead of a single classifier has been shown to improve generalization performance in many machine learning problems [4, 16]. However, the extent of such improvement depends greatly on the amount of correlation among the errors of the base classifiers [1, 14]. As such, reducing those correlations while keeping the base classifiers’ performance levels high is a ...

This paper evaluates the impact of the technology node on the area, performance and power consumption of a configurable VLSI architecture for Sum of Absolutes Differences (SAD). Such architecture may be configured to take benefit from pel decimation, trading off quality for energy. The proposed architecture was synthesized for 90nm and 65nm technologies assuming both nominal and Low-Vdd/High-Vt...

The convergence rate of the Least Mean Square (LMS) algorithm is dependent on the eigenvalue distribution of the reference input correlation matrix. When adaptive filters are employed in low-delay over-sampled subband structures, colored subband signals considerably decelerate the convergence speed. Here, we propose and implement two promising techniques for improving the convergence rate based...

This paper presents one method for a multiplierless FIR (finite impulse response) decimation filter design. The method is based on the IFIR (interpolated finite impulse response) structure and the sharpening techniques. It is supposed that the decimation factor can be presented as the product of two factors. In that way the expanded model filter can be moved to the lower rate. The coefficients ...

Decimation approaches for image processing have been widely used for various applications. For video processing, decimation refers to sampling the frame rate in order to reduce the number of processing frames. Most of these temporal decimation methods discard whole frames; as a result, some high-speed motions could be completely eliminated while some redundant frames might remain in the process...

Any digital processing performed on a signal with larger nyquist interval requires more computation than signal processing performed on smaller nyquist interval. The sampling rate alteration generates the unwanted effects in the system such as spectral aliasing and spectral imaging during signal processing. Multirate-multistage implementation of digital filter can result a significant computati...

We introduce an efficient message passing scheme for solving Constraint Satisfaction Problems (CSPs), which uses stochastic perturbation of Belief Propagation (BP) and Survey Propagation (SP) messages to bypass decimation and directly produce a single satisfying assignment. Our first CSP solver, called Perturbed Belief Propagation, smoothly interpolates two well-known inference procedures; it s...

We introduce an efficient message passing scheme for solving Constraint Satisfaction Problems (CSPs), which uses stochastic perturbation of Belief Propagation (BP) and Survey Propagation (SP) messages to bypass decimation and directly produce a single satisfying assignment. Our first CSP solver, called Perturbed Belief Propagation, smoothly interpolates two well-known inference procedures; it s...

Scaling up document-image classifiers to handle an unlimited variety of document and image types poses serious challenges to conventional trainable classifier technologies. Highly versatile classifiers demand representative training sets which can be dauntingly large: in investigating document content extraction systems, we have demonstrated the advantages of employing as many as a billion trai...

This paper addresses on three different architectures of digital decimation filter design of a multi-standard RF transceivers. Instead of using single stage decimation filter network, the filters are implemented in multiple stages using FPGA to optimize the area, delay and dynamic power consumption. The proposed decimation filter architectures reflect the considerable reduction in area and dyna...