forward-propagation networks
[/ˈfɔrwərd ˌprɑpəˈɡeɪʃən ˈnɛtˌwɜrks/]
nounpl: forward-propagation networks
redes de propagação direta
1. A type of artificial neural network architecture where information flows in one direction, from input layer through hidden layers to output layer, without feedback connections or cycles
Forward-propagation networks are the most common type of neural network used in supervised learning tasks.
As redes de propagação direta são o tipo mais comum de rede neural utilizado em tarefas de aprendizado supervisionado.
2. A feedforward neural network that uses the forward pass algorithm to compute outputs from inputs sequentially
In forward-propagation networks, each neuron's output depends only on its inputs and weights, not on future outputs.
Nas redes de propagação direta, a saída de cada neurônio depende apenas de suas entradas e pesos, não de saídas futuras.
This is a technical term predominantly used in computer science, artificial intelligence, and machine learning contexts. It is used uniformly across Brazil, Portugal, and the USA in academic and professional settings. The term reflects the mathematical and computational nature of neural network design, where 'forward-propagation' describes the computational flow from inputs to outputs without cycles or feedback loops.
Look up more words on Fala2Me
The free English-Portuguese dictionary with real Brazilian accents, NYC slang, conjugator and more
Open Fala2Me →