Deep Learning of Representations: Looking Forward
@inproceedings{Bengio2013DeepLO, title={Deep Learning of Representations: Looking Forward}, author={Yoshua Bengio}, booktitle={SLSP}, year={2013} }
- Published 2013 in SLSP
DOI:10.1007/978-3-642-39593-2_1
Deep learning research aims at discovering learning algorithms that discover multiple levels of distributed representations, with higher levels representing more abstract concepts. Although the study of deep learning has already led to impressive theoretical results, learning algorithms and breakthrough experiments, several challenges lie ahead. This paper proposes to examine some of these challenges, centering on the questions of scaling deep learning algorithms to much larger models and… CONTINUE READING
From This Paper
Topics from this paper.
Citations
Publications citing this paper.
Showing 1-10 of 168 extracted citations
Deep Learning Application in Security and Privacy - Theory and Practice: A Position Paper
View 4 Excerpts
Highly Influenced
Deep Learning for Sensor-based Activity Recognition: A Survey
View 6 Excerpts
Highly Influenced
What auto-encoders could learn from brains Generation as feedback in unsupervised deep learning and inference
View 13 Excerpts
Method Support
Highly Influenced
Estimating or Propagating Gradients Through Stochastic Neurons
View 6 Excerpts
Highly Influenced
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
View 4 Excerpts
Highly Influenced
Self-Normalizing Neural Networks
View 4 Excerpts
Highly Influenced
Learning Term Weights for Ad-hoc Retrieval
View 2 Excerpts
Highly Influenced
Travel intention-based attraction network for recommending travel destinations
View 2 Excerpts
Method Support
Highly Influenced
Spatial Deep Networks for Outdoor Scene Classification
View 3 Excerpts
Highly Influenced
Citation Statistics
365 Citations
Citations per Year
Semantic Scholar estimates that this publication has 365 citations based on the available data.
See our FAQ for additional information.
References
Publications referenced by this paper.
Showing 1-10 of 123 references
ImageNet Classification with Deep Convolutional Neural Networks
View 7 Excerpts
Highly Influenced
What regularized auto-encoders learn from the data-generating distribution
View 8 Excerpts
Highly Influenced
Better Mixing via Deep Representations
View 14 Excerpts
Highly Influenced
Generalized Denoising Auto-Encoders as Generative Models
View 14 Excerpts
Highly Influenced
Building high-level features using large scale unsupervised learning
View 5 Excerpts
Highly Influenced
Contractive Auto-Encoders: Explicit Invariance During Feature Extraction
View 5 Excerpts
Highly Influenced
Empirical Risk Minimization of Graphical Model Parameters Given Approximate Inference, Decoding, and Model Structure
View 6 Excerpts
Highly Influenced
The Manifold Tangent Classifier
View 4 Excerpts
Highly Influenced
Factored conditional restricted Boltzmann Machines for modeling motion style
View 26 Excerpts
Highly Influenced
Extracting and composing robust features with denoising autoencoders
View 4 Excerpts
Highly Influenced