• Publications
  • Influence
Marginalized Denoising Autoencoders for Domain Adaptation
Stacked denoising autoencoders (SDAs) have been successfully used to learn new representations for domain adaptation. Recently, they have attained record accuracy on standard benchmark tasks ofExpand
  • 560
  • 123
Fast Image Tagging
Automatic image annotation is a difficult and highly relevant machine learning task. Recent advances have significantly improved the state-of-the-art in retrieval accuracy with algorithms based onExpand
  • 179
  • 37
Co-Training for Domain Adaptation
Domain adaptation algorithms seek to generalize a model trained in a source domain to a new target domain. In many practical cases, the source and target distributions can differ substantially, andExpand
  • 288
  • 24
Learning with Marginalized Corrupted Features
The goal of machine learning is to develop predictors that generalize well to test data. Ideally, this is achieved by training on very large (infinite) training data sets that capture all variationsExpand
  • 130
  • 21
Efficient Vector Representation for Documents through Corruption
We present an efficient document representation learning framework, Document Vector through Corruption (Doc2VecC). Doc2VecC represents each document as a simple average of word embeddings. It ensuresExpand
  • 69
  • 17
Automatic Feature Decomposition for Single View Co-training
One of the most successful semi-supervised learning approaches is co-training for multi-view data. In co-training, one trains two classifiers, one for each view, and uses the most confidentExpand
  • 76
  • 14
AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
Recurrent neural networks have gained widespread use in modeling sequential data. Learning long-term dependencies using these models remains difficult though, due to exploding or vanishing gradients.Expand
  • 44
  • 10
Cost-Sensitive Tree of Classifiers
Recently, machine learning algorithms have successfully entered large-scale real-world industrial applications (e.g. search engines and email spam filters). Here, the CPU cost during test-time mustExpand
  • 88
  • 9
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks
Recurrent neural networks have gained widespread use in modeling sequence data across various domains. While many successful recurrent architectures employ a notion of gating, the exact mechanismExpand
  • 64
  • 9
Marginalized Denoising Auto-encoders for Nonlinear Representations
Denoising auto-encoders (DAEs) have been successfully used to learn new representations for a wide range of machine learning tasks. During training, DAEs make many passes over the training datasetExpand
  • 105
  • 7