# Lab : Distributed Algorithm - The "Bad" scenario.
## Overview
This project implements a **Sockets** based distributed algorithm for communication between nodes. The code is designed to be containerised using Docker and executed locally. The algorithm will later be used as a backbone for distributed federated learning.
This project implements a **Sockets** based distributed algorithm for communication between nodes. The code is designed to be containerised using Docker and executed locally. The algorithm will later be used as a backbone for a distributed federated learning approach used to improve the accuracy of edge devices (nodes).
This version only deals with the communicating messages between neighbors: there is no training. The messages will later contain the weight exchanges of local neural networks (NN) deployed on the nodes.
This version only deals with the communicating messages between neighbors: there is no forecasting. The messages will later contain the weight exchanges of local neural networks (NN) deployed on the nodes.