• Publications
  • Influence
Pruning Convolutional Neural Networks for Resource Efficient Inference
tl;dr
We propose a new criterion based on Taylor expansion that approximates the change in the cost function induced by pruning network parameters. Expand
  • 507
  • 71
Compressing Neural Networks with the Hashing Trick
tl;dr
We present a novel network architecture, HashedNets, that exploits inherent redundancy in neural networks to achieve drastic reductions in model sizes. Expand
  • 738
  • 43
  • Open Access
Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks
tl;dr
In this paper, we address these challenges with a recurrent three-dimensional convolutional neural network that performs simultaneous detection and classification of dynamic hand gestures from multi-modal data. Expand
  • 238
  • 40
  • Open Access
Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning
tl;dr
We propose a new framework for pruning convolutional kernels in neural networks to enable efficient inference, focusing on transfer learning where large and potentially unwieldy pretrained networks are adapted to specialized tasks. Expand
  • 237
  • 29
  • Open Access
Learning with Marginalized Corrupted Features
tl;dr
We propose to corrupt training examples with noise from known distributions within the exponential family and present a novel learning algorithm, called marginalized corrupted features (MCF), that trains robust predictors by minimizing the expected value of the loss function under the corrupting distribution. Expand
  • 134
  • 21
  • Open Access
Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
tl;dr
We introduce a hybrid CPU/GPU version of A3C, based on TensorFlow, achieves a significant speed up compared to a CPU implementation; we make it publicly available to other researchers at https://github.com/NVlabs/GA3C. Expand
  • 89
  • 17
  • Open Access
Non-linear Metric Learning
tl;dr
We introduce two novel metric learning algorithms, Χ2- LMNN and GB-LMNN, which are explicitly designed to be non-linear and easy-to-use. Expand
  • 161
  • 11
  • Open Access
Parallel boosted regression trees for web search ranking
tl;dr
We propose a novel method for parallelizing the training of GBRT, based on data partitioning, that achieves almost perfect linear speed-up with up to about 48 cores on the large data sets. Expand
  • 128
  • 11
  • Open Access
Stochastic Neighbor Compression
tl;dr
We present Stochastic Neighbor Compression (SNC), an algorithm to compress a dataset for the purpose of k-nearest neighbor (kNN) classification. Expand
  • 52
  • 9
  • Open Access
Improving Landmark Localization with Semi-Supervised Learning
tl;dr
We present two techniques to improve landmark localization in images from partially annotated datasets. Expand
  • 76
  • 8
  • Open Access