Pinned Repositories
advanced-pandas-experiments
analise_snis_datasus
api-express
Um repositório simples utilizado no curso denode.
app-tasks
App de tarefas desenvolvido em react-native acompanhando curso da Cod3r
curso-cplusplus
algumas implementações
gan-mnist-tensorflow
poo-cplusplus
pre_processing_data_weather
rnr-imdb
Rede Neural Recorrente (LSTM) para previsão de reviews no IMDB
weather_forecast
Previsão de temperatura, precipitação e velocidade do vento para uma cidade com ConvGRU
snovais's Repositories
snovais/weather_forecast
Previsão de temperatura, precipitação e velocidade do vento para uma cidade com ConvGRU
snovais/poo-cplusplus
snovais/advanced-pandas-experiments
snovais/analise_snis_datasus
snovais/pre_processing_data_weather
snovais/rnr-imdb
Rede Neural Recorrente (LSTM) para previsão de reviews no IMDB
snovais/arima
snovais/ASV-anti-spoofing-with-EABN
snovais/c-language
snovais/como_a_rede_neural_aprende
snovais/cplusplus_stl
snovais/CREMA-D
Crowd Sourced Emotional Multimodal Actors Dataset (CREMA-D)
snovais/design-patterns-python
snovais/feedforward_torch
snovais/intro-bert
snovais/intro_to_spark
snovais/introducao_pytorch
snovais/introduction_keras
snovais/KerasBeats
Github Repository for the KerasBeats package. Easily import and use the NBeats NN architecture in Keras
snovais/open_cv_hello_world_cpp
snovais/reconhecimento_de_audios
snovais/redes-neurais-com-numpy-para-regress-o
snovais/redes_neurais_recorrentes
snovais/segm_detectron2
snovais/snovais
snovais/tf-aprendizado-transferencia-classificacao-gato-cachorro
snovais/timehetnet
Learning complex time series forecasting models usually requires a large amount of data, as each model is trained from scratch for each task/data set. Leveraging learning experience with similar datasets is a well-established technique for classification problems called few-shot classification. However, existing approaches cannot be applied to time-series forecasting because i) multivariate time-series datasets have different channels and ii) forecasting is principally different from classification. In this paper we formalize the problem of few-shot forecasting of time-series with heterogeneous channels for the first time. Extending recent work on heterogeneous attributes in vector data, we develop a model composed of permutation-invariant deep set-blocks which incorporate a temporal embedding. We assemble the first meta-dataset of 40 multivariate time-series datasets and show through experiments that our model provides a good generalization, outperforming baselines carried over from simpler scenarios that either fail to learn across tasks or miss temporal information.
snovais/todo
snovais/UniCL_copy
Copy of The official implementation for "Unified Contrastive Learning in Image-Text-Label Space. CVPR 2022"
snovais/yolo_basic