Donate

sep 10, 2019 - 针对推导迁移学习的正则化使用论文里提出的 L2-SP 代替 L2 惩罚 A baseline regularization scheme for transfer learning with convolutional neural networks Xuhong Li, Yves Grandvalet, Franck Davoine 2019.9

文中指出 fine-tuning 可能会导致本来已学到的知识丢失。

13 Nov 2019

421

sep 10, 2019

Now

~ 6 years ago

Donate

The service accepts bank transfer (ACH, Wire) or cards (Visa, MasterCard, etc). Processed by Stripe.

Secured with SSL

sep 10, 2019 - 针对推导迁移学习的正则化 使用论文里提出的 L2-SP 代替 L2 惩罚 A baseline regularization scheme for transfer learning with convolutional neural networks Xuhong Li, Yves Grandvalet, Franck Davoine 2019.9