Fast and Robust Compression of Deep Convolutional Neural Networks

Mathematics

• Benchmark 32%
• Compression 100%
• Computing 20%
• Convolution 27%
• Decomposition Algorithm 39%
• Decomposition Method 35%
• Demonstrate 19%
• Experiment 24%
• Expressive Power 38%
• Framework 56%
• Image Classification 53%
• Neural Network Model 40%
• Neural Networks 92%
• Performance 19%
• Randomized Algorithms 35%
• Resources 61%
• Tensor Decomposition 95%
• Training 34%

Engineering & Materials Science

• Convolution 32%
• Convolutional neural networks 89%
• Data storage equipment 19%
• Decomposition 70%
• Deep neural networks 95%
• Experiments 11%
• Image classification 34%
• Tensors 64%