• Publications
  • Influence
Dropout: a simple way to prevent neural networks from overfitting
TLDR
It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
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 the
Unsupervised Learning of Video Representations using LSTMs
TLDR
This work uses Long Short Term Memory networks to learn representations of video sequences and evaluates the representations by finetuning them for a supervised learning problem - human action recognition on the UCF-101 and HMDB-51 datasets.
Multimodal learning with deep Boltzmann machines
TLDR
A Deep Boltzmann Machine is proposed for learning a generative model of multimodal data and it is shown that the model can be used to create fused representations by combining features across modalities, which are useful for classification and information retrieval.
Unsupervised Learning of Visual Representations using Videos
TLDR
This is a review of unsupervised learning applied to videos with the aim of learning visual representations to understand the challenges being faced, the strengths and weaknesses of different approaches and identify directions for future work.
Learning Representations for Multimodal Data with Deep Belief Nets
TLDR
The experimental results on bi-modal data consisting of images and text show that the Multimodal DBN can learn a good generative model of the joint space of image and text inputs that is useful for lling in missing data so it can be used both for image annotation and image retrieval.
Discriminative Transfer Learning with Tree-based Priors
TLDR
This work proposes a method for improving classification performance for high capacity classifiers by discovering similar classes and transferring knowledge among them, which learns to organize the classes into a tree hierarchy, and proposes an algorithm for learning the underlying tree structure.
Improving Neural Networks with Dropout
TLDR
In this work, models that improve the performance of neural networks using dropout are described, often obtaining state-of-the-art results on benchmark datasets.
Modeling Documents with Deep Boltzmann Machines
TLDR
A Deep Boltzmann Machine model suitable for modeling and extracting latent semantic representations from a large unstructured collection of documents is introduced and it is shown that the model assigns better log probability to unseen data than the Replicated Softmax model.
Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
TLDR
The proposed late fusion of CNN- and motion-based features can further increase the mean average precision (mAP) on MED'14 from 34.95% to 38.74% and achieves the state-of-the-art classification performance on the challenging UCF-101 dataset.
...
...