BengioY. x 29

bookRéférences 29

Dynamic inference with neural interpreters

… We believe that collaboration between scientists is paramount, and working in isolation...

2025-09-13 20:21:00

BengioY.GondalM.W.RahamanN.JoshiS.GehlerP.

On multiplicative integration with recurrent neural networks

We introduce a general simple structural design called “Multiplicative Integration&rdq...

2025-09-13 20:16:00

BengioY.ZhangS.WuY.ZhangY.

Evolving culture versus local minima

We propose a theory that relates difficulty of learning in deep architectures to culture and languag...

2025-09-13 20:14:00

BengioY.

Deep learning of representations: Looking forward

Deep learning research aims at discovering learning algorithms that discover multiple levels of dist...

2025-09-13 20:13:00

BengioY.

Disentangling factors of variation for facial expression recognition

… of emotion recognition in 2D face images using recent ideas in deep learning for handli...

2025-09-13 20:12:00

BengioY.CourvilleA.VincentP.RifaiS.

Practical recommendations for gradient-based training of deep architectures

Learning algorithms related to artificial neural networks and in particular for Deep Learning may se...

2025-09-13 20:12:00

BengioY.

On the expressive power of deep architectures

Deep architectures are families of functions corresponding to deep circuits. Deep Learning algorithm...

2025-09-13 20:11:00

BengioY.DelalleauO.

Semi-supervised learning by entropy minimization

We consider the semi-supervised learning problem, where a decision rule is to be learned from labele...

2025-09-13 20:04:00

BengioY.GrandvaletY.

Combining Parameter-efficient Modules for Task-level Generalisation

A modular design encourages neural models to disentangle and recombine different facets of knowledge...

2025-09-09 14:35:35

BengioY.SordoniA.PontiE.M.

Consciousness in artificial intelligence: Insights from the Science of consciousness

Whether current or near-term AI systems could be conscious is a topic of scientific interest and inc...

2023-08-22 20:33:30

BengioY.ElmozninoE.ButlinP.LongR.

Regeneration learning: A learning paradigm for data generation

Machine learning methods for conditional data generation usually build a mapping from source conditi...

2023-01-23 20:03:50

BengioY.TanX.QinT.BianJ.LiuT.Y.

Combining modular skills in multitask learning

A modular design encourages neural models to disentangle and recombine different facets of knowledge...

2022-03-01 20:29:34

BengioY.SordoniA.PontiE.M.ReddyS.

Predicting infectiousness for proactive contact tracing

… Little brother attacks include vigilante attacks: harassment, violence, hate crimes, or...

2020-10-25 20:24:14

BengioY.RahamanN.GuptaP.MaharajT.

Covi white paper

The SARS-CoV-2 (Covid-19) pandemic has caused significant strain on public health institutions aroun...

2020-07-27 20:42:45

BengioY.AlsdurfH.BelliveauE.DeleuT.

The variational bandwidth bottleneck: Stochastic evaluation on an information budget

In many applications, it is desirable to extract only the relevant information from complex input da...

2020-04-27 20:01:11

BengioY.GoyalA.BotvinickM.LevineS.

On the morality of artificial intelligence

Much of the existing research on the social and ethical impact of Artificial Intelligence has been f...

2019-12-29 20:13:52

BengioY.LuccioniA.

Learning general purpose distributed sentence representations via large scale multi-task learning

… We observe gains of 1.1-2.0% on the sentiment classification tasks (MR, CR, SUBJ &a...

2018-04-02 20:03:22

SubramanianS.TrischlerA.BengioY.

Learning anonymized representations with adversarial neural networks

… classification versus anonymization tasks (handwritten digits and sentiment analysis). ...

2018-02-26 20:18:56

BengioY.FeutryC.PiantanidaP.

How to construct deep recurrent neural networks

In this paper, we explore different ways to extend a recurrent neural network (RNN) to a extit{deep...

2014-04-24 20:09:18

BengioY.PascanuR.GulcehreC.ChoK.

Deep Learning of Representations: a AAAI 2013 Tutorial

… Domain adaptation for largescale sentiment classification: A deep learning approach. In...

2013-07-14 16:31:51

BengioY.

Better mixing via deep representations

… used to evaluate many deep learning algorithms, while the latter is interesting because...

2013-02-12 19:00:00

BengioY.MesnilG.DauphinY.

Disentangling factors of variation via generative entangling

… separate identity from emotion should perform well at the supervised learning task, whi...

2012-10-21 20:02:38

BengioY.CourvilleA.DesjardinsG.

Representation Learning and Deep Learning

… Domain adaptation for largescale sentiment classification: A deep learning approach. In...

2012-07-15 22:20:28

BengioY.

Deep learning of representations for unsupervised and transfer learning

… (2011b) applied stacked denoising auto-encoders with sparse rectifiers (the same as use...

2012-06-26 20:00:00

BengioY.

Representation Learning

… Domain adaptation for largescale sentiment classification: A deep learning approach. In...

2012-06-26 06:27:27

BengioY.

Deep sparse rectifier neural networks

While logistic sigmoid neurons are more biologically plausible than hyperbolic tangent neurons, the ...

2011-06-13 20:00:00

BengioY.GlorotX.BordesA.

Large-Scale Learning of Embeddings with Reconstruction Sampling.

In this paper, we present a novel method to speed up the learning of embeddings for large-scale lear...

2011-05-18 11:35:52

BengioY.GlorotX.DauphinY.N.

Domain adaptation for large-scale sentiment classification: A deep learning approach

… of research in sentiment classification (or sentiment analysis)… costly to d...

2011-05-18 11:35:24

BengioY.GlorotX.BordesA.

Artificial neural networks and their application to sequence recognition

This t. hf'sis studiell the introduct. ion of a priori structure into the design of learnin...

1991-09-13 13:49:23

BengioY.

Mots-clés associés