École Polytechnique de Montréal

About: École Polytechnique de Montréal is a education organization based out in Montreal, Quebec, Canada. It is known for research contribution in the topics: Finite element method & Computer science. The organization has 8015 authors who have published 18390 publications receiving 494372 citations.

Deep feature learning for automatic tissue classification of coronary artery using optical coherence tomography.

Abstract: Kawasaki disease (KD) is an acute childhood disease complicated by coronary artery aneurysms, intima thickening, thrombi, stenosis, lamellar calcifications, and disappearance of the media border. Automatic classification of the coronary artery layers (intima, media, and scar features) is important for analyzing optical coherence tomography (OCT) images recorded in pediatric patients. OCT has been known as an intracoronary imaging modality using near-infrared light which has recently been used to image the inner coronary artery tissues of pediatric patients, providing high spatial resolution (ranging from 10 to 20 μm). This study aims to develop a robust and fully automated tissue classification method by using the convolutional neural networks (CNNs) as feature extractor and comparing the predictions of three state-of-the-art classifiers, CNN, random forest (RF), and support vector machine (SVM). The results show the robustness of CNN as the feature extractor and random forest as the classifier with classification rate up to 96%, especially to characterize the second layer of coronary arteries (media), which is a very thin layer and it is challenging to be recognized and specified from other tissues.

Z-Forcing: Training Stochastic Recurrent Networks

Abstract: Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have been successful in capturing the variability observed in natural sequential data such as speech. We unify successful ideas from recently proposed architectures into a stochastic recurrent model: each step in the sequence is associated with a latent variable that is used to condition the recurrent dynamics for future steps. Training is performed with amortised variational inference where the approximate posterior is augmented with a RNN that runs backward through the sequence. In addition to maximizing the variational lower bound, we ease training of the latent variables by adding an auxiliary cost which forces them to reconstruct the state of the backward recurrent network. This provides the latent variables with a task-independent objective that enhances the performance of the overall model. We found this strategy to perform better than alternative approaches such as KL annealing. Although being conceptually simple, our model achieves state-of-the-art results on standard speech benchmarks such as TIMIT and Blizzard and competitive performance on sequential MNIST. Finally, we apply our model to language modeling on the IMDB dataset where the auxiliary cost helps in learning interpretable latent variables.