Home Explore Help
Sign In
CNI
/
NeuralNetwork
2
0
Fork 0
Files Issues 0 Pull Requests 0 Wiki
Browse Source

Use adapted gaussian deviation to initialize weights

DricomDragon 5 years ago
parent
e8cc1c94ba
commit
b18be6b40b
1 changed files with 1 additions and 1 deletions
Unified View Show Diff Stats
  1. 1 1
      python/start_session.py

+ 1 - 1
python/start_session.py
View File 

@@ -16,7 +16,7 @@ activationDerivative = lambda x : expit(x) * (1 - expit(x))
 
 epochs = 1
 
 epochs = 1
 
 
 
 # Session
 
 # Session
 
-network = generator.generate(activation, activationDerivative, generator.gaussUnitDev)
 
+network = generator.generate(activation, activationDerivative, generator.gaussAdaptedDev)
 
 
 
 precisionBefore = benchmark.computePrecision(network)
 
 precisionBefore = benchmark.computePrecision(network)