Realization of Stochastic Neural Networks and Its Potential Applications

TL;DR

This paper explores the implementation of stochastic neural networks as successive cancellation decoders, aiming to improve their efficiency and practicality for real-world applications.

Contribution

It introduces methods to realize stochastic neural networks on different platforms and discusses potential improvements for their performance.

Findings

Proposed realization methods for stochastic NNs on deterministic and stochastic platforms

Identified potential improvements for the efficiency of stochastic NNs as SC decoders

Highlighted practical considerations for implementing stochastic neural decoders

Abstract

Successive Cancellation Decoders have come a long way since the implementation of traditional SC decoders, but there still is a potential for improvement. The main struggle over the years was to find an optimal algorithm to implement them. Most of the proposed algorithms are not practical enough to be implemented in real-life. In this research, we aim to introduce the Efficiency of stochastic neural networks as an SC decoder and Find the possible ways of improving its performance and practicality. In this paper, after a brief introduction to stochastic neurons and SNNs, we introduce methods to realize Stochastic NNs on both deterministic and stochastic platforms.