BengioY. x 29
bookRéférences 29
Références · 2025-09-13
Dynamic inference with neural interpreters
… We believe that collaboration between scientists is paramount, and working in isolation...
Références · 2025-09-13
On multiplicative integration with recurrent neural networks
We introduce a general simple structural design called “Multiplicative Integration&rdq...
Références · 2025-09-13
Evolving culture versus local minima
We propose a theory that relates difficulty of learning in deep architectures to culture and languag...
Références · 2025-09-13
Deep learning of representations: Looking forward
Deep learning research aims at discovering learning algorithms that discover multiple levels of dist...
Références · 2025-09-13
Disentangling factors of variation for facial expression recognition
… of emotion recognition in 2D face images using recent ideas in deep learning for handli...
Références · 2025-09-13
Practical recommendations for gradient-based training of deep architectures
Learning algorithms related to artificial neural networks and in particular for Deep Learning may se...
Références · 2025-09-13
On the expressive power of deep architectures
Deep architectures are families of functions corresponding to deep circuits. Deep Learning algorithm...
Références · 2025-09-13
Semi-supervised learning by entropy minimization
We consider the semi-supervised learning problem, where a decision rule is to be learned from labele...
Références · 2025-09-09
Combining Parameter-efficient Modules for Task-level Generalisation
A modular design encourages neural models to disentangle and recombine different facets of knowledge...
Références · 2023-08-22
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...
Références · 2022-03-01
Combining modular skills in multitask learning
A modular design encourages neural models to disentangle and recombine different facets of knowledge...
Références · 2020-10-25
Predicting infectiousness for proactive contact tracing
… Little brother attacks include vigilante attacks: harassment, violence, hate crimes, or...
Références · 2020-07-27
The SARS-CoV-2 (Covid-19) pandemic has caused significant strain on public health institutions aroun...
Références · 2020-04-27
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...
Références · 2019-12-29
On the morality of artificial intelligence
Much of the existing research on the social and ethical impact of Artificial Intelligence has been f...
Références · 2018-04-02
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...
Références · 2018-02-26
Learning anonymized representations with adversarial neural networks
… classification versus anonymization tasks (handwritten digits and sentiment analysis). ...
Références · 2014-04-24
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...
Références · 2013-07-14
Deep Learning of Representations: a AAAI 2013 Tutorial
… Domain adaptation for largescale sentiment classification: A deep learning approach. In...
Références · 2013-02-12
Better mixing via deep representations
… used to evaluate many deep learning algorithms, while the latter is interesting because...
Références · 2012-10-21
Disentangling factors of variation via generative entangling
… separate identity from emotion should perform well at the supervised learning task, whi...
Références · 2012-07-15
Representation Learning and Deep Learning
… Domain adaptation for largescale sentiment classification: A deep learning approach. In...
Références · 2012-06-26
Deep learning of representations for unsupervised and transfer learning
… (2011b) applied stacked denoising auto-encoders with sparse rectifiers (the same as use...
Références · 2012-06-26
… Domain adaptation for largescale sentiment classification: A deep learning approach. In...
Références · 2011-06-13
Deep sparse rectifier neural networks
While logistic sigmoid neurons are more biologically plausible than hyperbolic tangent neurons, the ...
Références · 2011-05-18
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...
Références · 2011-05-18
Domain adaptation for large-scale sentiment classification: A deep learning approach
… of research in sentiment classification (or sentiment analysis)… costly to d...
Références · 1991-09-13
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...