# How to implement LSTM base meta relearning by Flux?

**URL:** https://discourse.julialang.org/t/how-to-implement-lstm-base-meta-relearning-by-flux/47164
**Category:** Machine Learning
**Tags:** lstm
**Created:** [September 23, 2020, 11:38pm UTC](https://discourse.julialang.org/t/how-to-implement-lstm-base-meta-relearning-by-flux/47164 "2020-09-23T23:38:32Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![nuclear718](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/nuclear718/32/16163_2.png) [@nuclear718](https://discourse.julialang.org/u/nuclear718)
#### Post date: [September 23, 2020, 11:38pm UTC](https://discourse.julialang.org/t/how-to-implement-lstm-base-meta-relearning-by-flux/47164/1 "2020-09-23T23:38:32Z")

</div>

In LSTM meta learning approach, we have a base leaner and update base learner’s parameters by another learner (single cell LSTM).  
The base learner’s parameters is LSTM’s cell state and will input LSTM one by one, the output cell state is a bit of optimized learner’s parameters…

How to feed cell state into LSTM cell and read it’s output? Not LSTM’s default output but cell state(c).  
Anyone has related examples?

Thanks.