作者
Yoshua Bengio
Machine Learning
On Random Weights for Texture Generation in One Layer Neural Networks
Comments ICASSP 2017
Generalizable Features From Unsupervised Learning
Invariant Representations for Noisy Speech Recognition
Comments 5 pages, 1 figure, 1 table, NIPS workshop on end-to-end speech recognition
On Multiplicative Integration with Recurrent Neural Networks
Comments 10 pages, 2 figures; To appear in NIPS2016
Architectural Complexity Measures of Recurrent Neural Networks
Comments 17 pages, 8 figures; To appear in NIPS2016
Describing Multimedia Content using Attention-based Encoder--Decoder Networks
Comments Submitted to IEEE Transactions on Multimedia Special Issue on Deep Learning for Multimedia Computing
Iterative Alternating Neural Attention for Machine Reading
Professor Forcing: A New Algorithm for Training Recurrent Networks
Comments NIPS 2016 Accepted Paper
Unitary Evolution Recurrent Neural Networks
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
Comments arXiv admin note: text overlap with arXiv:1602.02830
Oracle performance for visual captioning
Comments BMVC2016 (Oral paper)
Pointing the Unknown Words
Comments ACL 2016 Oral Paper
Mollifying Networks
Towards Biologically Plausible Deep Learning
HeMIS: Hetero-Modal Image Segmentation
Comments Accepted as an oral presentation at MICCAI 2016
Context-Dependent Word Representation for Neural Machine Translation
Comments 13 pages, 2 figures
Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible
Drawing and Recognizing Chinese Characters with Recurrent Neural Network
A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation
Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
Comments 21 pages, 2 figures, 10 tables
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
Comments 15 pages, 5 tables, 4 figures
Deep Directed Generative Models with Energy-Based Probability Estimation
Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus
Comments 13 pages, 1 figure, 7 tables
Bidirectional Helmholtz Machines
Hierarchical Memory Networks
Comments 10 pages
ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Comments In CVPR Deep Vision Workshop, 2016
Deconstructing the Ladder Network Architecture
Comments Proceedings of the 33 rd International Conference on Machine Learning, New York, NY, USA, 2016
