Y
Yoshua Bengio
Researcher at Université de Montréal
Publications - 1146
Citations - 534376
Yoshua Bengio is an academic researcher from Université de Montréal. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 202, co-authored 1033 publications receiving 420313 citations. Previous affiliations of Yoshua Bengio include McGill University & Centre de Recherches Mathématiques.
Papers
More filters
Posted Content
Small-GAN: Speeding Up GAN Training Using Core-sets
TL;DR: Experiments show that this technique substantially reduces training time and memory usage for modern GAN variants, that it reduces the fraction of dropped modes in a synthetic dataset, and that it allows GANs to reach a new state of the art in anomaly detection.
Proceedings Article
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
TL;DR: This work proposes a policy design that decomposes into primitives, similarly to hierarchical reinforcement learning, but without a high-level meta-policy, and uses an information-theoretic mechanism for enabling this decentralized decision.
Posted Content
Speech and Speaker Recognition from Raw Waveform with SincNet
Mirco Ravanelli,Yoshua Bengio +1 more
TL;DR: This paper proposes SincNet, a novel Convolutional Neural Network (CNN) that encourages the first layer to discover meaningful filters by exploiting parametrized sinc functions, and shows that the proposed architecture converges faster, performs better, and is more computationally efficient than standard CNNs.
Posted Content
Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation
Jean Pouget-Abadie,Dzmitry Bahdanau,Bart van Merriënboer,Kyunghyun Cho,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio +6 more
TL;DR: The authors propose to segment an input sentence into phrases that can be easily translated by the NMT model and concatenate the translated clauses to form a final translation, which shows a significant improvement in translation quality for long sentences.
Journal ArticleDOI
Alternative time representation in dopamine models.
TL;DR: A general rate-based learning model based on long short-term memory networks that learns a time representation when needed that reproduces the known finding that trace conditioning is more difficult than delay conditioning and that the learned representation of the task can be highly dependent on the types of trials experienced during training.