• Publications
  • Influence
Dropout: a simple way to prevent neural networks from overfitting
Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, makingExpand
  • 19,063
  • 1711
  • PDF
Improving neural networks by preventing co-adaptation of feature detectors
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of theExpand
  • 4,828
  • 421
  • PDF
Unsupervised Learning of Video Representations using LSTMs
We use Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length representation. ThisExpand
  • 1,427
  • 172
  • PDF
Multimodal learning with deep Boltzmann machines
Data often consists of multiple diverse modalities. For example, images are tagged with textual information and videos are accompanied by audio. Each modality is characterized by having distinctExpand
  • 1,265
  • 103
  • PDF
Unsupervised Learning of Visual Representations using Videos
This is a review of unsupervised learning applied to videos with the aim of learning visual representations. We look at different realizations of the notion of temporal coherence across variousExpand
  • 375
  • 35
  • PDF
Learning Representations for Multimodal Data with Deep Belief Nets
We propose a Deep Belief Network architecture for learning a joint representation of multimodal data. The model denes a probability distribution over the space of multimodal inputs and allowsExpand
  • 155
  • 29
  • PDF
Discriminative Transfer Learning with Tree-based Priors
High capacity classifiers, such as deep neural networks, often struggle on classes that have very few training examples. We propose a method for improving classification performance for such classesExpand
  • 164
  • 17
  • PDF
Improving Neural Networks with Dropout
Improving Neural Networks with Dropout Nitish Srivastava Master of Science Graduate Department of Computer Science University of Toronto 2013 Deep neural nets with a huge number of parameters areExpand
  • 186
  • 14
  • PDF
Modeling Documents with Deep Boltzmann Machines
We introduce a Deep Boltzmann Machine model suitable for modeling and extracting latent semantic representations from a large unstructured collection of documents. We overcome the apparent difficultyExpand
  • 108
  • 14
  • PDF
Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification. We study different ways ofExpand
  • 155
  • 7
  • PDF