kwargs neural

src/NeuralSurrogate.jl

@@ -21,13 +21,12 @@ mutable struct NeuralSurrogate{X,Y,M,L,O,P,N,A,U} <: AbstractSurrogate
  - opt: optimization function
 
  """
- function NeuralSurrogate(x,y,lb,ub,model,loss,opt,n_echos)
+ function NeuralSurrogate(x,y,lb,ub; model = Chain(Dense(length(x[1]),1), first), loss = (x,y) -> Flux.mse(model(x), y),opt = Descent(0.01),n_echos::Int = 1)
      X = vec.(collect.(x))
      data = zip(X, y)
      ps = Flux.params(model)
      @epochs n_echos Flux.train!(loss, ps, data, opt)
      return NeuralSurrogate(x,y,model,loss,opt,ps,n_echos,lb,ub)
-
  end
 
  function (my_neural::NeuralSurrogate)(val)

test/AD_compatibility.jl

@@ -227,11 +227,11 @@ g = x -> my_loba'(x)
 g(0.0)
 
 #NN
-model = Chain(Dense(1,1), first)
-loss(x, y) = Flux.mse(model(x), y)
-opt = Descent(0.01)
+my_model = Chain(Dense(1,1), first)
+my_loss(x, y) = Flux.mse(my_model(x), y)
+my_opt = Descent(0.01)
 n_echos = 1
-my_neural = NeuralSurrogate(x,y,lb,ub,model,loss,opt,n_echos)
+my_neural = NeuralSurrogate(x,y,lb,ub,model=my_model,loss=my_loss,opt=my_opt,n_echos=1)
 g = x->my_neural'(x)
 g(3.4)
 
@@ -283,11 +283,11 @@ g = x -> Zygote.gradient(my_second,x)
 g((2.0,5.0))
 
 #NN
-model = Chain(Dense(2,1), first)
-loss(x, y) = Flux.mse(model(x), y)
-opt = Descent(0.01)
+my_model = Chain(Dense(2,1), first)
+my_loss(x, y) = Flux.mse(my_model(x), y)
+my_opt = Descent(0.01)
 n_echos = 1
-my_neural = NeuralSurrogate(x,y,lb,ub,model,loss,opt,n_echos)
+my_neural = NeuralSurrogate(x,y,lb,ub,model=my_model,loss=my_loss,opt=my_opt,n_echos=1)
 g = x -> Zygote.gradient(my_neural, x)
 g((2.0,5.0))
 
@@ -301,11 +301,11 @@ f = x -> [x[1]^2, x[2]]
 y = f.(x)
 
 #NN
-model = Chain(Dense(2,2))
-loss(x, y) = Flux.mse(model(x), y)
-opt = Descent(0.01)
+my_model = Chain(Dense(2,2))
+my_loss(x, y) = Flux.mse(my_model(x), y)
+my_opt = Descent(0.01)
 n_echos = 1
-my_neural = NeuralSurrogate(x,y,lb,ub,model,loss,opt,n_echos)
+my_neural = NeuralSurrogate(x,y,lb,ub,model=my_model,loss=my_loss,opt=my_opt,n_echos=1)
 Zygote.gradient(x -> sum(my_neural(x)), (2.0, 5.0))
 
 my_rad = RadialBasis(x,y,lb,ub,rad = linearRadial)

test/neuralSurrogate.jl

@@ -8,11 +8,12 @@ b = 10.0
 obj_1D = x -> 2*x+3
 x = sample(10,0.0,10.,SobolSample())
 y = obj_1D.(x);
-model = Chain(Dense(1,1), first)
-loss(x, y) = Flux.mse(model(x), y)
-opt = Descent(0.01)
+my_model = Chain(Dense(1,1), first)
+my_loss(x, y) = Flux.mse(my_model(x), y)
+my_opt = Descent(0.01)
 n_echos = 1
-my_neural = NeuralSurrogate(x,y,a,b,model,loss,opt,n_echos)
+my_neural = NeuralSurrogate(x,y,a,b,model = my_model,loss = my_loss,opt = my_opt,n_echos=1)
+my_neural_kwargs = NeuralSurrogate(x,y,a,b)
 add_point!(my_neural,8.5,20.0)
 add_point!(my_neural,[3.2,3.5],[7.4,8.0])
 val = my_neural(5.0)
@@ -24,11 +25,12 @@ ub = [5.0,5.0]
 x = sample(5,lb,ub, SobolSample())
 obj_ND_neural(x) = x[1]*x[2];
 y = obj_ND_neural.(x)
-model = Chain(Dense(2,1), first)
-loss(x, y) = Flux.mse(model(x), y)
-opt = Descent(0.01)
+my_model = Chain(Dense(2,1), first)
+my_loss(x, y) = Flux.mse(my_model(x), y)
+my_opt = Descent(0.01)
 n_echos = 1
-my_neural = NeuralSurrogate(x,y,lb,ub,model,loss,opt,n_echos)
+my_neural = NeuralSurrogate(x,y,lb,ub,model=my_model,loss=my_loss,opt=my_opt,n_echos=1)
+my_neural_kwargs = NeuralSurrogate(x,y,lb,ub)
 my_neural((3.5, 1.49))
 my_neural([3.4,1.4])
 add_point!(my_neural,(3.5,1.4),4.9)
@@ -41,19 +43,21 @@ ub = 10.0
 x  = sample(5, lb, ub, SobolSample())
 push!(x, 2.0)
 y  = f.(x)
-model = Chain(Dense(1,2))
-loss(x, y) = Flux.mse(model(x), y)
-surrogate = NeuralSurrogate(x,y,lb,ub,model,loss,opt,n_echos)
+my_model = Chain(Dense(1,2))
+my_loss(x, y) = Flux.mse(my_model(x), y)
+surrogate = NeuralSurrogate(x,y,lb,ub,model = my_model,loss = my_loss ,opt=my_opt,n_echos=1)
+surr_kwargs = NeuralSurrogate(x,y,lb,ub)
 
 f  = x -> [x[1], x[2]^2]
 lb = [1.0, 2.0]
 ub = [10.0, 8.5]
 x  = sample(20, lb, ub, SobolSample())
 push!(x, (1.0, 2.0))
 y  = f.(x)
-model = Chain(Dense(2,2))
-loss(x, y) = Flux.mse(model(x), y)
-surrogate = NeuralSurrogate(x,y,lb,ub,model,loss,opt,n_echos)
+my_model = Chain(Dense(2,2))
+my_loss(x, y) = Flux.mse(my_model(x), y)
+surrogate = NeuralSurrogate(x,y,lb,ub,model=my_model,loss=my_loss,opt=my_opt,n_echos=1)
+surrogate_kwargs = NeuralSurrogate(x,y,lb,ub)
 surrogate((1.0, 2.0))
 x_new = (2.0, 2.0)
 y_new = f(x_new)

test/optimization.jl

@@ -88,7 +88,7 @@ model = Chain(Dense(2,1), first)
 loss(x, y) = Flux.mse(model(x), y)
 opt = Descent(0.01)
 n_echos = 1
-my_neural_ND_neural = NeuralSurrogate(x,y,lb,ub,model,loss,opt,n_echos)
+my_neural_ND_neural = NeuralSurrogate(x,y,lb,ub)
 surrogate_optimize(objective_function_ND,SRBF(),lb,ub,my_neural_ND_neural,SobolSample(),maxiters=15)
 
 #Random Forest