Deep Layered LMS Predictor

2019/05/11 by Mokatren, Lubna Shibly, Cetin, Ahmet Enis, Ansari, Rashid
#FOS: Electrical engineering #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1905.04596

Abstract

In this study, we present a new approach to design a Least Mean Squares (LMS) predictor. This approach exploits the concept of deep neural networks and their supremacy in terms of performance and accuracy. The new LMS predictor is implemented as a deep neural network using multiple non linear LMS filters. The network consists of multiple layers with nonlinear activation functions, where each neuron in the hidden layers corresponds to a certain FIR filter output which goes through nonlinearity. The output of the last layer is the prediction. We hypothesize that this approach will outperform the traditional adaptive filters.

Related

• Performance analysis of LMS adaptive prediction filters
• Improving Levenberg-Marquardt Algorithm for Neural Networks
• Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation
• Nonlinear Prediction of Multidimensional Signals via Deep Regression with Applications to Image Coding
• Multilinear Map Layer: Prediction Regularization by Structural Constraint