-
Notifications
You must be signed in to change notification settings - Fork 0
Yi Zhu edited this page Mar 29, 2021
·
3 revisions
GA
is Genetic Algorithm.
GA.fit(;models::Array, input_data::Array{Float32}, output_data::Array{Float32}, loss_function::Any, monitor::Any, α::Float64=0.01, gene_pool::Int64, num_copy::Int64, epochs::Int64=20, batch::Real=32, mini_batch::Int64=5)
models
: an array of 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
: mutation rate, default 0.01
gene_pool
: the number of models
num_copy
: the number of models that will be copied into the next round directly
epochs
: number of training epochs, default 20
batch
: the number of batches for each training epoch, default 32
mini_batch
: the size of minibatch for each update, default 5
Star the repo if you like it! :-)