Softmax as logistic function

[maomran]

Hi, I have two questions:

1. After training mnist, the testing it gets me average accurage of 0.3, any ideas why?
2. Activations are updated by calculating the cost and applying a logistic function, why is a softmax used instead of sigmoid?

[www0wwwjs1]

Hi,

1. Basically, you can use the hyper parameters given in the readme file for similar performance on mnist. Other parameters may lead to failure in training.
2. Sigmoid function can give a similar performance according to our experiments. Softmax here just theoretically ensures a distribution over capsules.