# Deep Modulation Embedding

## TL;DR

This paper explores an unsupervised deep learning approach for modulation recognition, introducing new features and loss functions, and evaluates robustness under various mismatch conditions, advancing communication system applications.

## Contribution

It presents a novel unsupervised deep learning framework for modulation recognition, differing from traditional supervised classification methods.

## Key findings

- Effective in recognizing modulation schemes without labeled data
- Robust against various mismatch conditions
- Outperforms some existing supervised methods in certain scenarios

## Abstract

Deep neural network has recently shown very promising applications in different research directions and attracted the industry attention as well. Although the idea was introduced in the past but just recently the main limitation of using this class of algorithms is solved by enabling parallel computing on GPU hardware. Opening the possibility of hardware prototyping with proven superiority of this class of algorithm, trigger several research directions in communication system too. Among them cognitive radio, modulation recognition, learning based receiver and transceiver are already given very interesting result in simulation and real experimental evaluation implemented on software defined radio. Specifically, modulation recognition is mostly approached as a classification problem which is a supervised learning framework. But it is here addressed as an unsupervised problem with introducing new features for training, a new loss function and investigating the robustness of the pipeline against several mismatch conditions.