# Pull to the manifold autoencoder compressive sensing

**URL:** <https://discourse.numenta.org/t/pull-to-the-manifold-autoencoder-compressive-sensing/2090>\
**Category:** Lounge\
**Created:** [April 4, 2017, 11:38pm UTC](https://discourse.numenta.org/t/pull-to-the-manifold-autoencoder-compressive-sensing/2090 "2017-04-04T23:38:16Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sean\_O\_Connor](https://avatars.discourse-cdn.com/v4/letter/s/34f0e0/32.png) [@Sean\_O\_Connor](https://discourse.numenta.org/u/Sean_O_Connor)\
**Post date:** [April 4, 2017, 11:38pm UTC](https://discourse.numenta.org/t/pull-to-the-manifold-autoencoder-compressive-sensing/2090/1 "2017-04-04T23:38:16Z")

</div>

I hope this works out well when I code it:  
[https://groups.google.com/forum/#!topic/artificial-general-intelligence/NLqBlanCSHw](https://groups.google.com/forum/#!topic/artificial-general-intelligence/NLqBlanCSHw)  
It actually should be possible to use it with a selection of autoencoders operating at different scales somewhat like a convolutional network. Let’s see.

---

<div class="post-metadata">

**Author:** ![Sean\_O\_Connor](https://avatars.discourse-cdn.com/v4/letter/s/34f0e0/32.png) [@Sean\_O\_Connor](https://discourse.numenta.org/u/Sean_O_Connor)\
**Post date:** [April 5, 2017, 8:34am UTC](https://discourse.numenta.org/t/pull-to-the-manifold-autoencoder-compressive-sensing/2090/2 "2017-04-05T08:34:15Z")

</div>

It looks like it works out okay-ish. You should try with a better autoencoder though.  
[https://drive.google.com/open?id=0BwsgMLjV0BnhaFNLTEt1TmN5YTA](https://drive.google.com/open?id=0BwsgMLjV0BnhaFNLTEt1TmN5YTA)