function mySqrt(x)
    ans = (x + 1) / 2
    for _ in 1:10
        ans = (ans + x / ans) / 2
    end
    ans
end
    
x = (0.1 : 0.3 : 4) .± 0.2
y = mySqrt.(x)

scatter(x, y
  , legend = false
  , xlabel = L"x"
  , ylabel = L"\sqrt x"
)

using GaussianMixtures: GMM
using ScikitLearn

gmm = fit!(GMM(n_components=3, kind=:diag), X)
predict_proba(gmm, X)

i = tf.constant(0, name="i")
result = tf.constant(0, name="result")

output = tf.while_loop(
  lambda i, result: tf.less(i, 10), 
  lambda i, result: [i+1, result+tf.pow(i,2)], 
  [i, result]
)

@tf i = constant(0)
@tf result = constant(0)
output = @tf while i < 10
  i_sq = i^2
  [i=>i+1, result=>result+i_sq]
end

using MXNet

mlp = @mx.chain mx.Variable(:data)             =>
  mx.FullyConnected(name=:fc1, num_hidden=128) =>
  mx.Activation(name=:relu1, act_type=:relu)   =>
  mx.FullyConnected(name=:fc2, num_hidden=64)  =>
  mx.Activation(name=:relu2, act_type=:relu)   =>
  mx.FullyConnected(name=:fc3, num_hidden=10)  =>
  mx.SoftmaxOutput(name=:softmax)

# data provider
batch_size = 100
include(Pkg.dir("MXNet", "examples", "mnist", "mnist-data.jl"))
train_provider, eval_provider = get_mnist_providers(batch_size)

# setup model
model = mx.FeedForward(mlp, context=mx.cpu())

# optimization algorithm
# where η is learning rate and μ is momentum
optimizer = mx.SGD(η=0.1, μ=0.9)

# fit parameters
mx.fit(model, optimizer, train_provider, n_epoch=20, eval_data=eval_provider)