<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Neural-Networks on Scholion</title><link>https://scholion.thluiz.com/tags/neural-networks/</link><description>Recent content in Neural-Networks on Scholion</description><generator>Hugo -- gohugo.io</generator><language>pt-BR</language><copyright>© 2026</copyright><lastBuildDate>Wed, 23 Sep 2026 15:42:10 +0100</lastBuildDate><atom:link href="https://scholion.thluiz.com/tags/neural-networks/index.xml" rel="self" type="application/rss+xml"/><item><title>News Feature: What are the limits of deep learning?</title><link>https://scholion.thluiz.com/notes/news-feature-what-are-the-limits-of-deep-learning/</link><pubDate>Wed, 23 Sep 2026 15:38:15 +0100</pubDate><guid>https://scholion.thluiz.com/notes/news-feature-what-are-the-limits-of-deep-learning/</guid><description>PNAS profile of 2019 surveys where deep learning breaks: adversarial spoofing, data inefficiency, opacity, and the missing common sense that symbolic AI once tried to hand-code.</description></item></channel></rss>