Corpus ID: 29683894

- LEVEL ACCURACY WITH 50 X FEWER PARAMETERS AND < 0 . 5 MB MODEL SIZE

@inproceedings{Iandola2016LA,
  title={- LEVEL ACCURACY WITH 50 X FEWER PARAMETERS AND < 0 . 5 MB MODEL SIZE},
  author={Forrest N. Iandola and Song Han and M. Moskewicz and Khalid Ashraf and W. Dally and K. Keutzer},
  year={2016}
}
Recent research on deep convolutional neural networks (CNNs) has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple CNN architectures that achieve that accuracy level. With equivalent accuracy, smaller CNN architectures offer at least three advantages: (1) Smaller CNNs require less communication across servers during distributed training. (2) Smaller CNNs require less bandwidth to export a new model from the cloud to an autonomous… Expand
666 Citations

Figures and Tables from this paper

SEP-Nets: Small and Effective Pattern Networks
Shallow SqueezeNext: An Efficient & Shallow DNN
BINARY DEEP NEURAL NETWORKS
Towards Robust Compressed Convolutional Neural Networks
Compression of convolutional neural networks: A short survey
Reducing SqueezeNet Storage Size with Depthwise Separable Convolutions
Training Compact Neural Networks with Binary Weights and Low Precision Activations
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 45 REFERENCES
Convolutional neural networks at constrained time cost
  • Kaiming He, Jian Sun
  • Computer Science
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
Going Deeper with Embedded FPGA Platform for Convolutional Neural Network
Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks
Very Deep Convolutional Networks for Large-Scale Image Recognition
Deep Residual Learning for Image Recognition
ImageNet classification with deep convolutional neural networks
Rethinking the Inception Architecture for Computer Vision
Caffe: Convolutional Architecture for Fast Feature Embedding
Learning both Weights and Connections for Efficient Neural Network
...
1
2
3
4
5
...