models_speedup.md

Here the brief list of existed models speedup techniques with the links:

• Compression
  • Quantization
    • Quantized Convolutional Neural Networks for Mobile Devices
  • hashing
    • Compressing Neural Networks with the Hashing Trick
  • Pruning
    • Learning both Weights and Connections for Efficient Neural Networks
    • Pruning Convolutional Neural Networks for Resource Efficient Inference
  • Vector quantization
    • Compressing Deep Convolutional Networks using Vector Quantization
  • Huffman coding
    • Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
  • Factorizations
    • Speeding up Convolutional Neural Networks with Low Rank Expansions
    • Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
    • Ultimate tensorization: compressing convolutional and FC layers alike
• Knowledge distillation
  • Distilling the Knowledge in a Neural Network
  • Sequence-Level Knowledge Distillation
• low bit networks
  • Training deep neural networks with low precision multiplications
  • XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
  • Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• I don't know exactly
  • Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications

Blog posts:

• How to Quantize Neural Networks with TensorFlow
• Compression of neural networks
• Compressing and regularizing deep neural networks
• Deep Compression and EIE slides and video
• Pruning deep neural networks to make them fast and small(in pyTorch)

Comment/contributing are welcome!