# Building an embedding layer

**URL:** <https://community.konduit.ai/t/building-an-embedding-layer/847>\
**Category:** DL4J\
**Created:** [September 9, 2020, 5:24am UTC](https://community.konduit.ai/t/building-an-embedding-layer/847 "2020-09-09T05:24:17Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![jin](https://avatars.discourse-cdn.com/v4/letter/j/4af34b/32.png) [@jin](https://community.konduit.ai/u/jin)\
**Post date:** [September 9, 2020, 5:24am UTC](https://community.konduit.ai/t/building-an-embedding-layer/847/1 "2020-09-09T05:24:17Z")

</div>

I would like to build an embedding layer to implement time to vector embedding per this paper:

> **[1907.05321.pdf](https://arxiv.org/pdf/1907.05321.pdf)**
>
> 994.68 KB

What is the right starting point to implement my class? Should I extend org.deeplearning4j.nn.conf.layers.FeedForwardLayer or extend org.deeplearning4j.nn.layers.BaseLayer? What are the methods that I need to override? Thanks for any pointer.

---

<div class="post-metadata">

**Author:** ![eduardo](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/eduardo/32/24_2.png) [@eduardo](https://community.konduit.ai/u/eduardo)\
**Post date:** [September 16, 2020, 3:18am UTC](https://community.konduit.ai/t/building-an-embedding-layer/847/2 "2020-09-16T03:18:25Z")

</div>

The easiest way to do this these days is to subclass SameDiffLambdaLayer. See the examples here: [deeplearning4j-examples/L2NormalizeLambdaLayer.java at master · eclipse/deeplearning4j-examples · GitHub](https://github.com/eclipse/deeplearning4j-examples/blob/master/samediff-examples/src/main/java/org/nd4j/examples/samediff/customizingdl4j/layers/L2NormalizeLambdaLayer.java)