• 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.
Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation
TLDR
This work proposes a novel semi-supervised image segmentation method that simultaneously optimizes a supervised segmentation and an unsupervised reconstruction objectives and analyzes the features learned by different methods and finds that the attention mechanism helps to learn more discriminative features in the deeper layers of encoders.
Question Classification by Weighted Combination of Lexical, Syntactic and Semantic Features
TLDR
A learning-based question classifier for question answering systems that extracted several lexical, syntactic and semantic features and developed a weighting approach to combine features based on their importance.
Combining Generative and Discriminative Representation Learning for Lung CT Analysis With Convolutional Restricted Boltzmann Machines
TLDR
This paper proposes the convolutional classification restricted Boltzmann machine, which combines a generative and a discriminative learning objective, which allows it to learn filters that are good both for describing the training data and for classification.
Combining Generative and Discriminative Representation Learning for Lung CT Analysis With Convolutional Restricted Boltzmann Machines.
TLDR
This paper proposes the convolutional classification restricted Boltzmann machine, which combines a generative and a discriminative learning objective, which allows it to learn filters that are good both for describing the training data and for classification.
Why Does Synthesized Data Improve Multi-sequence Classification?
TLDR
Experiments with two classifiers, linear support vector machines SVMs and random forests, together with two synthesis methods that can replace missing data in an image classification problem: neural networks and restricted Boltzmann machines RBMs are presented.
Learning Features for Tissue Classification with the Classification Restricted Boltzmann Machine
TLDR
It is found that R BM-learned features outperform conventional RBM-based feature learning, which is unsupervised and uses only a generative learning objective, as well as often-used filter banks.
Learning Cross-Modality Representations From Multi-Modal Images
TLDR
A shared autoencoder-like convolutional network that learns a common representation from multi-modal data is presented, and a form of feature normalization, a learning objective that minimizes cross-modality differences, and modality dropout are investigated, in which the network is trained with varying subsets of modalities.
Learning Cross-Modality Representations From Multi-Modal Images
TLDR
A shared autoencoder-like convolutional network that learns a common representation from multi-modal data is presented, and a form of feature normalization, a learning objective that minimizes cross-modality differences, and modality dropout are investigated, in which the network is trained with varying subsets of modalities.
...
...