Inicio Explorar Axuda
Iniciar sesión
CNI
/
NeuralNetwork
2
0
Fork 0
Ficheiros Incidencias 0 Pull Requests 0 Wiki
Explorar o código

Use adapted gaussian deviation to initialize weights

DricomDragon %!s(int64=5) %!d(string=hai) anos
pai
e8cc1c94ba
achega
b18be6b40b
Modificáronse 1 ficheiros con 1 adicións e 1 borrados
Dividir vista Mostrar estatísticas de Diff
  1. 1 1
      python/start_session.py

+ 1 - 1
python/start_session.py
Ver ficheiro 

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