Corpus ID: 649645

Fixed Point Quantization of Deep Convolutional Networks

@article{Lin2016FixedPQ,
  title={Fixed Point Quantization of Deep Convolutional Networks},
  author={D. D. Lin and S. Talathi and V. Annapureddy},
  journal={ArXiv},
  year={2016},
  volume={abs/1511.06393}
}
In recent years increasingly complex architectures for deep convolution networks (DCNs) have been proposed to boost the performance on image recognition tasks. [...] Key Result In doing so, we report a new state-of-the-art fixed point performance of 6.78% error-rate on CIFAR-10 benchmark.Expand
505 Citations
Space Efficient Quantization for Deep Convolutional Neural Networks
  • 4
Towards Lower Bit Multiplication for Convolutional Neural Network Training
  • 4
  • PDF
IFQ-Net: Integrated Fixed-Point Quantization Networks for Embedded Vision
  • 7
  • Highly Influenced
  • PDF
Deep Convolutional Neural Network Inference with Floating-point Weights and Fixed-point Activations
  • 61
  • Highly Influenced
  • PDF
Rethinking floating point for deep learning
  • 67
  • PDF
FixCaffe: Training CNN with Low Precision Arithmetic Operations by Fixed Point Caffe
  • 4
Zero-Centered Fixed-Point Quantization With Iterative Retraining for Deep Convolutional Neural Network-Based Object Detectors
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 34 REFERENCES
Fixed point optimization of deep convolutional neural networks for object recognition
  • 162
  • Highly Influential
Compressing Deep Convolutional Networks using Vector Quantization
  • 729
  • PDF
A Deep Neural Network Compression Pipeline: Pruning, Quantization, Huffman Encoding
  • 49
  • PDF
Overcoming Challenges in Fixed Point Training of Deep Convolutional Networks
  • 29
  • PDF
Very Deep Convolutional Networks for Large-Scale Image Recognition
  • 47,433
  • Highly Influential
  • PDF
Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding
  • 4,407
  • PDF
Deep Learning with Limited Numerical Precision
  • 1,234
  • PDF
Improving the speed of neural networks on CPUs
  • 603
  • PDF
Low precision arithmetic for deep learning
  • 158
Training deep neural networks with low precision multiplications
  • 398
  • PDF
...
1
2
3
4
...