Tweeted By @maithra_raghu
Do Wide and Deep neural networks Learn the Same Things?
— Maithra Raghu (@maithra_raghu) October 30, 2020
Paper: https://t.co/tnLUsKrNo5
We study representational properties of neural networks with different depths and widths on CIFAR/ImageNet, with insights on model capacity effects, feature similarity & characteristic errors https://t.co/YdsuRy6SBt