April 2025
Intermediate to advanced
478 pages
11h 57m
Portuguese (Portugal, Brazil)
Content preview from Inteligência Artificial nas Finanças
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 7. Redes neurais densas
Este trabalho foi traduzido com recurso a IA. Agradecemos o teu feedback e comentários: translation-feedback@oreilly.com
[Se tentares prever os movimentos de uma ação no mercado de acções com base no seu histórico recente de preços, é pouco provável que tenhas sucesso, porque o histórico de preços não contém muita informação preditiva.
François Chollet (2017)
Este capítulo trata de aspectos importantes das redes neuronais densas. Os capítulos anteriores já utilizaram este tipo de rede neural. Em particular, os modelosMLPClassifier e MLPRegressor de scikit-learn e o modelo Sequential de Keras para classificação e estimativa são redes neurais densas (DNNs). Este capítulo centra-se exclusivamente em Keras, uma vez que dá mais liberdade e flexibilidade na modelação de DNNs.1
"Os Dados" apresenta o conjunto de dados de divisas (FX) que as outras secções deste capítulo utilizam. "Previsão de Base" gera uma previsão de base, na amostra, no novo conjunto de dados. A normalização dos dados de treino e de teste é introduzida em "Normalização". Como forma de evitar o sobreajuste, "Dropout" e "Regularization" discutem o dropout e a regularização como métodos populares. Bagging, outro método para evitar o sobreajuste e já utilizado no Capítulo 6, é revisitado em "Bagging". Finalmente, "Optimizers" compara o desempenho de diferentes optimizadores que podem ser utilizados com os modelos Keras DNN.
Embora a citação introdutória do capítulo possa dar poucas razões ...
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.