发帖
雷达卡
On Exact Computation with an Infinitely Wide
Neural Net
Sanjeev Arora Simon S. Du Wei Hu§ Zhiyuan Li
Ruslan Salakhutdinovk Ruosong Wang
Abstract
How well does a classic deep net architecture like AlexNet or VGG19 classify on a
standard dataset such as CIFAR-10 when its “width”— namely, number of channels
in convolutional layers, and number of nodes in fully-connected internal layers —
...
京公网安备 11010802022788号
