• Publications
  • Influence
Theano: A Python framework for fast computation of mathematical expressions
TLDR
The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed. Expand
A Structured Self-attentive Sentence Embedding
TLDR
A new model for extracting an interpretable sentence embedding by introducing self-attention is proposed, which uses a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence. Expand
Deep Learning-Based Classification of Hyperspectral Data
TLDR
The concept of deep learning is introduced into hyperspectral data classification for the first time, and a new way of classifying with spatial-dominated information is proposed, which is a hybrid of principle component analysis (PCA), deep learning architecture, and logistic regression. Expand
Neural Language Modeling by Jointly Learning Syntax and Lexicon
TLDR
A novel neural language model, called the Parsing-Reading-Predict Networks (PRPN), that can simultaneously induce the syntactic structure from unannotated sentences and leverage the inferred structure to learn a better language model is proposed. Expand
Towards Biologically Plausible Deep Learning
TLDR
The theory about the probabilistic interpretation of auto-encoders is extended to justify improved sampling schemes based on the generative interpretation of denoising auto- Encoder, and these ideas are validated on generative learning tasks. Expand
Architectural Complexity Measures of Recurrent Neural Networks
TLDR
This paper proposes three architecture complexity measures of RNNs and rigorously proves each measure's existence and computability, and demonstrates that increasing recurrent skip coefficient offers performance boosts on long term dependency problems. Expand
Neural Networks with Few Multiplications
TLDR
Experimental results show that this approach to training that eliminates the need for floating point multiplications can result in even better performance than standard stochastic gradient descent training, paving the way to fast, hardware-friendly training of neural networks. Expand
Straight to the Tree: Constituency Parsing with Neural Syntactic Distance
TLDR
This work proposes a novel constituency parsing scheme that achieves the state-of-the-art single model F1 score of 92.1 on PTB and 86.4 on CTB dataset, which surpasses the previous single model results by a large margin. Expand
A Deep Reinforcement Learning Chatbot
TLDR
MILA's MILABOT is capable of conversing with humans on popular small talk topics through both speech and text and consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. Expand
Spectral-spatial classification of hyperspectral image using autoencoders
TLDR
A new framework of spectral-spatial feature extraction for HSI classification, in which for the first time the concept of deep learning is introduced, and achieves the highest classification accuracy among all methods, and outperforms classical classifiers such as SVM and PCA-based SVM. Expand
...
1
2
3
4
...