23 feb 2015 año - Speeding-up convolutional neural networks using fine-tuned cp-decomposition (ICLR 2014)
Descripción:
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.
Añadido al timeline:
fecha:
23 feb 2015 año
Ahora mismo
~ 10 years ago