Community Profile

photo

Arman Ahmadian


Last seen: 3 meses hace Con actividad desde 2021

Followers: 0   Following: 0

Estadísticas

Feeds

Ver por

Pregunta


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...

más de 2 años hace | 1 respuesta | 0

1

respuesta

Pregunta


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 ...

más de 2 años hace | 0 respuestas | 1

0

respuestas