hard20 pts · first answer countsdeep-learninginitialisation
Initialising a tanh network
For a layer with fan_in = 256 and fan_out = 256 using tanh, Xavier (Glorot) normal initialisation uses variance 2 / (fan_in + fan_out). What standard deviation does that give?
Discussion 0
Join free to post in the discussion.
Related questions
- Parameters in nn.Linear(10, 5)Machine Learning Engineer
- Why sigmoid slows deep trainingMachine Learning Engineer
- Range of tanhMachine Learning Engineer
- Cross-entropy loss by handMachine Learning Engineer
- Telling autograd to track a tensorMachine Learning Engineer
- Why wrap inference in no_gradMachine Learning Engineer
- Logging loss without leaking memoryMachine Learning Engineer
- Feeding a single image to a CNNMachine Learning Engineer