joint representation learning
[/dʒɔɪnt ˌrɛprɪˈzɛnˈteɪʃən ˈlɜrnɪŋ/]
noun
aprendizado de representação conjunta
1. A machine learning technique where multiple related tasks or modalities are learned simultaneously to create shared representations that capture common features across different domains or data types
Joint representation learning allows the model to learn from both images and text simultaneously, improving performance on multimodal tasks.
O aprendizado de representação conjunta permite que o modelo aprenda de imagens e texto simultaneamente, melhorando o desempenho em tarefas multimodais.
2. In deep learning, a framework where a single neural network learns to encode information from multiple sources or tasks into a common latent space
The researchers used joint representation learning to train a model on both video and audio data.
Os pesquisadores usaram aprendizado de representação conjunta para treinar um modelo em dados de vídeo e áudio.
This is a technical term primarily used in artificial intelligence and machine learning research communities in both Brazil and the USA. It reflects the globalization of AI terminology, where Portuguese-speaking researchers use this term interchangeably with English in academic papers and conferences.
Look up more words on Fala2Me
The free English-Portuguese dictionary with real Brazilian accents, NYC slang, conjugator and more
Open Fala2Me →