Recently, recursive least square (RLS), or extended Kalman ltering (EKF), based algorithms have been demonstrated to be a class of eeective online training methods for neural networks. This paper discusses several aspects of pruning a neural network trained by the RLS based approach. Based on our study, the RLS approach is implicitly a weight decay training algorithm. Also, we derive two prunin...

In this contribution, a covariance counterpart is described of the information matrix approach to constrained recursive least squares estimation. Unlike information-type algorithms, covariance algorithms are amenable to parallel implementation, e.g. on processor arrays, and this is also demonstrated. As compared to previously described combined covariance-information algorithms/arrays, the pres...

This paper presents a linear parameter estimation technique used to estimate the rotor resistance, self inductance of the rotor winding, stator resistance and the stator leakage inductance of an induction motor. Such estimation is important for achieving high estimation performance of induction motor drives. The parameters estimation model expresses the relationships of the dynamic machine mode...

The present work describes the implementation of a faster converging adaptive filter through the recursive least square algorithm for one dimensional signals denoising such as sinusoidal and audio signals i.e., to obtain an original sinusoidal signal and the audio signal back from the signal which was corrupted using a random noise .The application had been performed over an FPGA (field-program...

Classifying non-stationary and imbalanced data streams encompasses two important challenges, namely concept drift and class imbalance. ‘‘Concept drift’’ (or nonstationarity) is changes in the underlying function being learnt, and class imbalance is vast difference between the numbers of instances in different classes of data. Class imbalance is an obstacle for the efficiency of most classifiers...

A recursive least square RLS algorithm for estimation of vehicle sideslip angle and road friction coefficient is proposed. The algorithm uses the information from sensors onboard vehicle and control inputs from the control logic and is intended to provide the essential information for active safety systems such as active steering, direct yaw moment control, or their combination. Based on a simp...

A recursive formulation of an exponential smoothing filter is developed, within the framework of a least square error approach with data uncertainties that increase exponentially with time. An efficient implementation into Java is presented. By analogy to the Kalman filter, an interpretation of the gain as a ratio of uncertainties leads to a measure of validity for the recursive exponential fil...

The performance of multiuser adaptive minimum mean square error (MMSE) receiver combined with multiple antennas is investigated for wideband code division multiple access systems (W-CDMA) in multipath fading channels. In the adaptive implementation of the receiver, performance of various algorithms like least mean square (LMS), normalized least mean square (NLMS), recursive least square (RLS) a...