Lucca Gamballi, Daniel G. Tiglea, Renato Candido, Magno T. M. Silva. Treinamento distribuído de redes MLP para classificação de figuras geométricas, Simpósio Brasileiro de Telecomunicações – SBrT’2022, 2022. Santa Rita do Sapucaí, Anais do SBrT 2022, 2022, pp. 1–2. (available only in portuguese)

Abstract

Multilayer perceptron neural networks are used to classify geometric figures using a distributed approach. Training data are divided among neural networks that communicate through a certain topology, in which each network does not have access to the training data of the others. Simulation results indicate that the performance achieved with distributed training and a suitable topology is similar to that observed with classical training. Thus, data privacy is guaranteed without loss of performance.

Keywords

Artificial neural networks, multi-layer perceptron, distributed processing, topology, geometric figures.

Downloads

• PDF