# Flux.params does not recognize parameters with \`x -\> layer(x)\` syntax

**URL:** <https://discourse.julialang.org/t/flux-params-does-not-recognize-parameters-with-x-layer-x-syntax/46832>\
**Category:** Machine Learning\
**Tags:** flux\
**Created:** [September 18, 2020, 9:37am UTC](https://discourse.julialang.org/t/flux-params-does-not-recognize-parameters-with-x-layer-x-syntax/46832 "2020-09-18T09:37:24Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![tgrassi](https://avatars.discourse-cdn.com/v4/letter/t/0ea827/32.png) [@tgrassi](https://discourse.julialang.org/u/tgrassi)\
**Post date:** [September 18, 2020, 10:14am UTC](https://discourse.julialang.org/t/flux-params-does-not-recognize-parameters-with-x-layer-x-syntax/46832/3 "2020-09-18T10:14:57Z")

</div>

Hi @tomerarnon,  
thanks for the prompt clarification!

As I mentioned in the question, the issue is relative to [#18877](https://discourse.julialang.org/t/flux-concatenate-layers/18877) where in the proposed solution the parameters are “recognized” only in the layers `D` and `E`, and not in `A*`, `B*`, and `C*`. From their discussion it seems that this wasn’t the intended behavior, since probably the other layers should also be trainable.

---

_[View the full topic](https://discourse.julialang.org/t/flux-params-does-not-recognize-parameters-with-x-layer-x-syntax/46832)._