FIR neural networks are feedforward neural networks with regular scalar synapses replaced by linear finite impulse response filters. This paper introduces the Second Order Temporal Backpropagation algorithm which enables the exact calculation of the second order error derivatives for a FIR neural network. This method is based on the error gradient calculation method first proposed by Wan and re...

Digital filter plays an important role in Very Large Scale Integration (VLSI) technology. The existing Finite Impulse Response (FIR) filter has long transient response which is the major limitation. To overcome this drawback, Residue Number System (RNS) based FIR filters is developed which is described in this paper. High-speed is obtained by introducing the residue arithmetic concept that perm...

We present a new method for general multidimensional multichannel deconvolution with finite impulse response (FIR) convolution and deconvolution filters using Gröbner bases. Previous work formulates the problem of multichannel FIR deconvolution as the construction of a left inverse of the convolution matrix, which is solved by numerical linear algebra. However, this approach requires the prior ...

This paper introduces a class of reconfigurable two-stage Nyquist filters where the Farrow structure realizes the polyphase components of linear-phase finite-length impulse response (FIR) filters. By adjusting the variable predetermined multipliers of the Farrow structure, various linear-phase FIR Nyquist filters and integer interpolation/decimation structures are obtained, online. However, the...

We present the design of two dimensional finite impulse response(FIR) signal adapted filter banks for an input signal whose power spectral density is separable. One dimensional FIR filters are designed for each of the separable components using iterative greedy algorithm. The first and last filters in this 2D filter bank are found to be separable and matching closely with ideal ones .The remain...

Bandpass filters (BPFs) are very important to extract target signals and eliminate noise from the received signals. A BPF of which frequency characteristics is a sum Gaussian functions called mixture (GMBPF). In this research, we propose implement GMBPF approximately by several components sliding Fourier transform (SFT) or attenuated SFT (ASFT). Because component SFT/ASFT can be realized using ...

Based on symmetry of the maximally flat frequency response of a FIR notch filter the new design procedure is developed. The closed form solution provides direct computation of the frequency response, recursive computation of the impulse response coefficients, simple windowing technique, and an access to new implementation. Several examples are included. INTRODUCTION In order to remove a single ...

A class of infinite impulse response (IIR) perfect reconstruction (PR) filterbank is obtained with an allpass delay chain and finite impulse response (FIR) matrices at the analysis side. Such a formulation leads to a filterbank that can be optimized to any desired response. For a first-order allpass, the synthesis bank becomes FIR. Design examples showing warping of the frequency scale and filt...

In this paper we introduce the generalized feedforward filter, a new class of adaptive filters that combine attractive properties of Finite Impulse Response (FIR) filters with some of the power of Infinite Impulse Response (IIR) filters. A particular case, the adaptive gamma filter, generalizes Widrow’s adaptive linear combiner (adaline) to an infinite impulse response filter. Yet, the stabilit...

PSM architecture synthesizes multiplier blocks with low hardware requirement suitable for implementation as part of full parallel finite impulse response (FIR) filters is presented in this paper. FIR digital filters are widely used in DSP by the virtue of its stability, linear phase, fewer finite precision error and efficient implementation. In this paper, new reconfigurable architectures of lo...