class Num::NN::SGDMomentumOptimizer(T)
- Num::NN::SGDMomentumOptimizer(T)
- Num::NN::Optimizer(T)
- Reference
- Object
Defined in:
nn/optimizers/sgd.crConstructors
Instance Method Summary
- #build_params(l : Array(Layer(T)))
- #decay : Float64
- #learning_rate : Float64
- #moments : Array(T)
- #momentum : Float64
- #nesterov : Bool
- #params : Array(Num::Grad::Variable(T))
- #update
Instance methods inherited from class Num::NN::Optimizer(T)
build_params(l : Array(Layer(T)))
build_params,
learning_rate : Float64
learning_rate,
params : Array(Num::Grad::Variable(T))
params,
update
update
Constructor methods inherited from class Num::NN::Optimizer(T)
new(learning_rate : Float64 = 0.01)
new
Constructor Detail
def self.new(learning_rate : Float64, momentum : Float64 = 0.0, decay : Float64 = 0.0, nesterov : Bool = false)
#