A Deep Learning MIMO Communication System Based on Auto-encoder Design

Please enable javascript in your browser.

Mirzaee, Ali | 2020

254 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 53583 (05)
University: Sharif University of Technology
Department: Electrical Engineering
Advisor(s): Hossein Khalaj, Babak
Abstract:
Today, the use of deep learning algorithms in the design of communication systems has received much attention. One of these areas is the partial or total design of these systems using deep networks. The overall design of a communication system using deep networks allows for global optimization and can provide better performance in cases where classical methods have suboptimal performance without significantly increasing the computational load. In this research, a comprehensive architecture for designing communication systems based on Auto-encoder neural networks is presented. This architecture has the same functionality as classical systems, considering all parts of these systems including transmitter, receiver, modulation, beamforming and channel as a matter of classification and optimization, and offers better performance than existing methods in multi-user MIMO mode
Keywords:
Deep Learning ; Neural Network ; Beamforming ; Communication System ; Cooperative Multiple Input Multiple Output (MIMO)System ; Autoencoder

No TOC