아티히어로

CIFAR10

• Pruning Filters while Training for Efficiently Optimizing Deep Learning Networks

  ARXIV/Convolution Neural Network 2020. 3. 8. 14:53

  https://arxiv.org/abs/2003.02800v1 Pruning Filters while Training for Efficiently Optimizing Deep Learning Networks Modern deep networks have millions to billions of parameters, which leads to high memory and energy requirements during training as well as during inference on resource-constrained edge devices. Consequently, pruning techniques have been proposed that remo arxiv.org abstract 현대의 딥 ..

  Read More
• Neural Kernels Without Tangents

  ARXIV/Neural Network 2020. 3. 7. 22:08

  https://arxiv.org/abs/2003.02237v2

  Read More