Search Results for author: Nicolas Chapados

Found 10 papers, 3 papers with code

TACTiS: Transformer-Attentional Copulas for Time Series

no code implementations7 Feb 2022 Alexandre Drouin, Étienne Marcotte, Nicolas Chapados

The estimation of time-varying quantities is a fundamental component of decision making in fields such as healthcare and finance.

Decision Making Time Series

Meta-learning framework with applications to zero-shot time-series forecasting

2 code implementations7 Feb 2020 Boris N. Oreshkin, Dmitri Carpov, Nicolas Chapados, Yoshua Bengio

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?

Meta-Learning Time Series +1

Learning to Learn with Conditional Class Dependencies

no code implementations ICLR 2019 Xiang Jiang, Mohammad Havaei, Farshid Varno, Gabriel Chartrand, Nicolas Chapados, Stan Matwin

Neural networks can learn to extract statistical properties from data, but they seldom make use of structured information from the label space to help representation learning.

Few-Shot Learning Representation Learning

CASED: Curriculum Adaptive Sampling for Extreme Data Imbalance

no code implementations27 Jul 2018 Andrew Jesson, Nicolas Guizard, Sina Hamidi Ghalehjegh, Damien Goblot, Florian Soudan, Nicolas Chapados

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 imbalance.

Lung Nodule Detection

Adversarially Learned Mixture Model

no code implementations14 Jul 2018 Andrew Jesson, Cécile Low-Kam, Tanya Nair, Florian Soudan, Florent Chandelier, Nicolas Chapados

The Adversarially Learned Mixture Model (AMM) is a generative model for unsupervised or semi-supervised data clustering.

On the Importance of Attention in Meta-Learning for Few-Shot Text Classification

no code implementations3 Jun 2018 Xiang Jiang, Mohammad Havaei, Gabriel Chartrand, Hassan Chouaib, Thomas Vincent, Andrew Jesson, Nicolas Chapados, Stan Matwin

Based on the Model-Agnostic Meta-Learning framework (MAML), we introduce the Attentive Task-Agnostic Meta-Learning (ATAML) algorithm for text classification.

Classification Few-Shot Text Classification +6

HeMIS: Hetero-Modal Image Segmentation

1 code implementation18 Jul 2016 Mohammad Havaei, Nicolas Guizard, Nicolas Chapados, Yoshua Bengio

We introduce a deep learning image segmentation framework that is extremely robust to missing imaging modalities.

Imputation Semantic Segmentation

Effective Bayesian Modeling of Groups of Related Count Time Series

no code implementations15 May 2014 Nicolas Chapados

Time series of counts arise in a variety of forecasting applications, for which traditional models are generally inappropriate.

Time Series

Cannot find the paper you are looking for? You can Submit a new open access paper.