MCPcopy Create free account
hub / github.com/MichalDanielDobrzanski/DeepLearningPython / large_weight_initializer

Method large_weight_initializer

network2.py:103–121  ·  view source on GitHub ↗

Initialize the weights using a Gaussian distribution with mean 0 and standard deviation 1. Initialize the biases using a Gaussian distribution with mean 0 and standard deviation 1. Note that the first layer is assumed to be an input layer, and by convention we

(self)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected