feb 23, 2015 - Speeding-up convolutional neural networks using fine-tuned cp-decomposition (ICLR 2014)
Description:
Four-component Decomposition结果：
For the standard ImageNet architecture (AlexNet), the approach speeds up the second convolution layer by a factor of 4x at the cost of 1% increase of the overall top-5 classification error.
Added to timeline:
Date:
feb 23, 2015
Now
~ 10 years ago