Simple Regression using "layers.combinators.Parallel"

[aycandv]

Description

I was trying to perform a simple optimization using Parallel combinator other than Serial. By using Dense layers in Serial, it is trivial to optimize. However, I could not see any optimization while using two Dense layers in Parallel.

Here is the desired model:

layer = tl.Parallel(
    tl.Dense(1, use_bias=False),
    tl.Dense(1, use_bias=False)
)

I could not see the point where I am wrong. Here is the link to my code: https://colab.research.google.com/drive/1dCVORQC5TjpvDCgRfM66iRuKEfIgkaBj?usp=sharing

Appreciate any help