snovais

snovais's Stars

• NVIDIA/cuda-samples

  Samples for CUDA Developers which demonstrates features in CUDA Toolkit

  Language:C6.2k1.8k

• radrumond/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.

  Language:Python409

• CheyneyComputerScience/CREMA-D

  Crowd Sourced Emotional Multimodal Actors Dataset (CREMA-D)

  Language:R353118

• big-data-lab-team/openpain-subacute_longitudinal_study

  A Datalad dataset for OpenPain's subacute_longitudinal_study dataset (http://openpain.org), for integration in CONP (http://conp.ca)

  13

• tensorflow/models

  Models and examples built with TensorFlow

  Language:Python77k45.8k

• big-data-lab-umbc/edask

  Earth data analytics using the Dask / XArray toolkit.

  1

• big-data-lab-umbc/big-data-deep-learning-4-satellite-data

  Language:Jupyter Notebook21

• kelvins/design-patterns-python

  :computer: Padrões de Projeto em Python

  Language:Python502114

• jeremykawahara/ann4brains

  Artificial neural networks for brain networks

  Language:Python7125

• xnd-r/4D_interpolation_polynomial

  Language:C++1

• DurhamDecLab/ARBInterp

  Tricubic and quadcubic spline interpolation for 3D and 4D vector and scalar fields

  Language:Python389

• eriklindernoren/Keras-GAN

  Keras implementations of Generative Adversarial Networks.

  Language:Python9.2k3.1k

• hugorichard/multiviewica

  MultiViewICA: Modeling shared sources

  Language:Python293

• nilearn/nilearn

  Machine learning for NeuroImaging in Python

  Language:Python1.2k595

• MRegina/numpy_array_to_tfrecords

  TFRecord converter for numpy array data (e.g. 3D images for medical image processing)

  Language:Python8

• MRegina/connectome_conv_net

  Connectome-convolutional neural netvork for connectivity-based classificatin

  Language:Python3817

• MRegina/rest_to_task

  3D convolutional neural network to predict individual task activations based on resting state connectivity maps

  Language:Python11

• MRegina/DTW_for_fMRI

  Language:MATLAB63

• kaloraat/react-node-ecommerce

  React Node Ecommerce with Paypal and Credit Card payments with Admin Order Management System

  Language:JavaScript280198

• the-akira/Python-Matematica

  Explorando aspectos fundamentais da matemática com Python e Jupyter

  Language:Jupyter Notebook5611

• filipecavalc/Algoritmo-neuro-evolutivo-aplicado-a-mecanica-de-um-jogo-2D

  A neuro-evolução é uma técnica de aprendizado de máquina que aplica algoritmos evolucionários para construir uma rede neural artificial, tendo como inspiração o processo biológico evolutivo do sistema nervoso na natureza.

  Language:Python61

• marcoscastro/mochila_inteiro-busca_tabu

  Busca tabu resolvendo o problema da mochila inteira

  55

• lucasgomide/videos-pt.br-tecnologia

  Repositório de canais no Youtube BR sobre desenvolvimento

  Language:Ruby2.5k287