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
On multiplicative integration with recurrent neural networks
We introduce a general simple structural design called “Multiplicative Integration&rdq...
2025-09-13 20:16:00
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
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
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
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
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
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
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
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
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
Predicting infectiousness for proactive contact tracing
… Little brother attacks include vigilante attacks: harassment, violence, hate crimes, or...
2020-10-25 20:24:14
The SARS-CoV-2 (Covid-19) pandemic has caused significant strain on public health institutions aroun...
2020-07-27 20:42:45
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
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
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
Learning anonymized representations with adversarial neural networks
… classification versus anonymization tasks (handwritten digits and sentiment analysis). ...
2018-02-26 20:18:56
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
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
Better mixing via deep representations
… used to evaluate many deep learning algorithms, while the latter is interesting because...
2013-02-12 19:00:00
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
Representation Learning and Deep Learning
… Domain adaptation for largescale sentiment classification: A deep learning approach. In...
2012-07-15 22:20:28
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
… Domain adaptation for largescale sentiment classification: A deep learning approach. In...
2012-06-26 06:27:27
Deep sparse rectifier neural networks
While logistic sigmoid neurons are more biologically plausible than hyperbolic tangent neurons, the ...
2011-06-13 20:00:00
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
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
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