Sparse Signal Recovery for Binary Compressed Sensing by Majority Voting Neural Networks

TL;DR

This paper introduces majority voting neural networks for binary compressed sensing, demonstrating that an appropriate loss function and ensemble approach significantly improve sparse signal recovery performance.

Contribution

The paper proposes a novel ensemble neural network method with a specialized loss function for enhanced binary sparse signal recovery.

Findings

Majority voting neural networks outperform single networks in recovery accuracy.

A loss function combining cross entropy and L1 regularization is most effective.

Performance approaches optimal as the number of component networks increases.

Abstract

In this paper, we propose majority voting neural networks for sparse signal recovery in binary compressed sensing. The majority voting neural network is composed of several independently trained feedforward neural networks employing the sigmoid function as an activation function. Our empirical study shows that a choice of a loss function used in training processes for the network is of prime importance. We found a loss function suitable for sparse signal recovery, which includes a cross entropy-like term and an $L_1$ regularized term. From the experimental results, we observed that the majority voting neural network achieves excellent recovery performance, which is approaching the optimal performance as the number of component nets grows. The simple architecture of the majority voting neural networks would be beneficial for both software and hardware implementations.