average pooling
[/ˈævərɪdʒ ˈpuːlɪŋ/]
noun
pooling médio
1. A machine learning and neural network technique that reduces the spatial dimensions of feature maps by calculating the average value of elements within a defined window or kernel, commonly used in convolutional neural networks for downsampling
Average pooling with a 2x2 kernel computes the mean of four adjacent pixel values to reduce the image size.
O pooling médio com um kernel 2x2 calcula a média de quatro valores de pixels adjacentes para reduzir o tamanho da imagem.
2. A downsampling operation that helps reduce computational complexity and prevents overfitting by decreasing the number of parameters in a neural network
The convolutional layer is followed by average pooling to extract dominant features.
A camada convolucional é seguida por pooling médio para extrair características dominantes.
Average pooling is a technical term primarily used in artificial intelligence and machine learning communities. It is widely used in academic and professional settings in both Brazil and the USA without translation, though Brazilian Portuguese texts may use 'pooling médio' for clarity. The term reflects the global nature of AI development and research, where English terminology dominates regardless of regional context.
Look up more words on Fala2Me
The free English-Portuguese dictionary with real Brazilian accents, NYC slang, conjugator and more
Open Fala2Me →