<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>1D Convolutional Networks | Jorge Kamassury — Academic CV</title><link>https://kamassury.github.io/tags/1d-convolutional-networks/</link><atom:link href="https://kamassury.github.io/tags/1d-convolutional-networks/index.xml" rel="self" type="application/rss+xml"/><description>1D Convolutional Networks</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>pt-br</language><lastBuildDate>Sun, 29 Sep 2019 00:00:00 +0000</lastBuildDate><image><url>https://kamassury.github.io/media/icon_hu_982c5d63a71b2961.png</url><title>1D Convolutional Networks</title><link>https://kamassury.github.io/tags/1d-convolutional-networks/</link></image><item><title>Classificação Automática de Modulações usando Redes Convolucionais 1D</title><link>https://kamassury.github.io/publications/conference-paper/sbrt-modulations-2019/</link><pubDate>Sun, 29 Sep 2019 00:00:00 +0000</pubDate><guid>https://kamassury.github.io/publications/conference-paper/sbrt-modulations-2019/</guid><description>&lt;p&gt;Estudo comparativo de &lt;strong&gt;arquiteturas convolucionais 1D&lt;/strong&gt; (CNN, ResNet e rede híbrida ResNet+DenseNet) para classificação automática de modulações. O trabalho demonstra que, em comparação com redes neurais convolucionais 2D tradicionais, as abordagens propostas atingem acurácias próximas ou superiores com &lt;strong&gt;tempos de treinamento consistentemente menores&lt;/strong&gt;.&lt;/p&gt;</description></item></channel></rss>