Arman Ahmadian

Last seen: 5 days 前 | 自 2021 起处于活动状态

Followers: 0 Following: 0

统计学

Feeds

提问

Can automatic differentiation in a custom deep learning layer keep track of the random numbers generated in the forward function of the layer?
I'm trying to create a gating neural network (NN) to use in a Mixture of Experts (MoE) settings a schematic of similar to what i...

3 years 前 | 1 个回答 | 0

1

个回答

提问

When used in DDPG actor and critics networks, the 1×1 convolution does NOT behave like a fully connected layer (Even though it should). Why is that?
Supposing (for some valid reason), my data is arranged along the third dimension. Say x = rand(1,1,m); I need to process this ...

3 years 前 | 0 个回答 | 1

0

个回答