April 2025
Intermediate to advanced
416 pages
8h 32m
Portuguese (Portugal, Brazil)
Content preview from Livro de receitas de aprendizagem automática com Python, 2ª edição
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Capítulo 21. Redes neurais
Este trabalho foi traduzido com recurso a IA. Agradecemos o teu feedback e comentários: translation-feedback@oreilly.com
21.0 Introdução
No coração das redes neurais básicas está a unidade (também chamada de nó ou neurônio). Uma unidade recebe uma ou mais entradas, multiplica cada entrada por um parâmetro (também chamado de peso), soma os valores da entrada ponderada com algum valor de polarização (normalmente 0) e, em seguida, alimenta o valor em uma função de ativação. Esta saída é então enviada para os outros neurónios mais profundos da rede neuronal (se existirem).
As redes neurais podem ser visualizadas como uma série de camadas conectadas que formam uma rede que liga os valores das caraterísticas de uma observação numa extremidade e o valor-alvo (por exemplo, a classe da observação) na outra extremidade. As redes neurais feedforward - também chamadas de perceptron multicamadas - sãoas redes neurais artificiais mais simples usadas em qualquer ambiente do mundo real. O nome "feedforward" vem do facto de os valores das caraterísticas de uma observação serem alimentados "para a frente" através da rede, com cada camada a transformar sucessivamente os valores das caraterísticas com o objetivo de que a saída seja igual (ou próxima) do valor alvo.
Especificamente, as redes neuronais feedforward contêm três tipos de camadas. No início da rede neural, há uma camada de entrada, em que cada unidade contém o valor de uma observação para uma única caraterística. ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.