4 papers
Meta-learning framework with applications to zero-shot time-series forecasting
Boris N. Oreshkin, Dmitri Carpov, Nicolas Chapados +1
Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets? This…
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
Boris N. Oreshkin, Dmitri Carpov, Nicolas Chapados +1
We focus on solving the univariate times series point forecasting problem using deep learning. We propose a deep neural architecture based on backward and forward residual links an…
CASED: Curriculum Adaptive Sampling for Extreme Data Imbalance
Andrew Jesson, Nicolas Guizard, Sina Hamidi Ghalehjegh +3
We introduce CASED, a novel curriculum sampling algorithm that facilitates the optimization of deep learning segmentation or detection models on data sets with extreme class imbala…
On the Importance of Attention in Meta-Learning for Few-Shot Text Classification
Xiang Jiang, Mohammad Havaei, Gabriel Chartrand +5
Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by…