SGD

SGD is Stochastic Gradient Descent.

SGD.fit(;model::Any, input_data::Array{Float32}, output_data::Array{Float32}, loss_function::Any, monitor::Any, α::Float64=0.01, epochs::Int64=20, batch::Real=32)

model: any sequential models

input_data: a 2-dimensional input data in a shape of (,batch_size)

output_data: a 2-dimensional output data in a shape of (,batch_size)

loss_function: a loss function

monitor: a monitor

α: learning rate, default 0.01

epochs: number of training epochs, default 20

batch: the number of batches for training, default 32