# Deep Learning and Artificial Intelligence with Elixir **URL:** \ **Category:** Discussions\ **Tags:** machine-learning\ **Created:** [February 23, 2017, 8:46am UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818 "2017-02-23T08:46:27Z")\ **Posts on this page:** 9\ **Page:** 1
**Author:** ![TheQuengineer](https://forum.elixirforum.com/user_avatar/forum.elixirforum.com/thequengineer/32/3448_2.png) [@TheQuengineer](https://forum.elixirforum.com/u/TheQuengineer)\ **Post date:** [February 23, 2017, 8:46am UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818/1 "2017-02-23T08:46:27Z")
I’m currently working on several Neural Networks using Elixir and Erlang’s OTP ecosystem. I recently just finished an example project called Deepnet. It’s one example of a 3 x 3 architecture. There are many more Network types I’m exploring. Here is a link to the post [here](http://www.automatingthefuture.com/blog/2017/2/20/deep-learning-building-and-training-a-multi-layered-neural-network-in-elixir) for anyone interested in this topic. ---
**Author:** ![krapans](https://forum.elixirforum.com/user_avatar/forum.elixirforum.com/krapans/32/3866_2.png) [@krapans](https://forum.elixirforum.com/u/krapans)\ **Post date:** [February 23, 2017, 8:52am UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818/2 "2017-02-23T08:52:20Z")
Looks cool, what’s your end goal with this? I mean what’s your project goal. ---
**Author:** ![ssagaert](https://forum.elixirforum.com/user_avatar/forum.elixirforum.com/ssagaert/32/12848_2.png) [@ssagaert](https://forum.elixirforum.com/u/ssagaert)\ **Post date:** [February 23, 2017, 8:55am UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818/3 "2017-02-23T08:55:36Z")
I wouldn’t exactly call a 3x3 network “deep”… ---
**Author:** ![TheQuengineer](https://forum.elixirforum.com/user_avatar/forum.elixirforum.com/thequengineer/32/3448_2.png) [@TheQuengineer](https://forum.elixirforum.com/u/TheQuengineer)\ **Post date:** [February 23, 2017, 8:57am UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818/4 "2017-02-23T08:57:01Z")
That’s fair, Deep as in more than one Layer. ---
**Author:** ![TheQuengineer](https://forum.elixirforum.com/user_avatar/forum.elixirforum.com/thequengineer/32/3448_2.png) [@TheQuengineer](https://forum.elixirforum.com/u/TheQuengineer)\ **Post date:** [February 23, 2017, 9:06am UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818/5 "2017-02-23T09:06:06Z")
Right now, it’s about building different networks while testing their performance and finding limitations. Eventually, I’d like to do a major system written entirely in Elixir. ---
**Author:** ![krapans](https://forum.elixirforum.com/user_avatar/forum.elixirforum.com/krapans/32/3866_2.png) [@krapans](https://forum.elixirforum.com/u/krapans)\ **Post date:** [February 23, 2017, 9:15am UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818/6 "2017-02-23T09:15:37Z")
Ok sounds good. I would love to see more information about your journey over the time. 👍 ---
**Author:** ![ssagaert](https://forum.elixirforum.com/user_avatar/forum.elixirforum.com/ssagaert/32/12848_2.png) [@ssagaert](https://forum.elixirforum.com/u/ssagaert)\ **Post date:** [February 23, 2017, 8:21pm UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818/7 "2017-02-23T20:21:54Z")
I took a look at the Matrix library you rely on… It’s a nested list! =\> this project has zero chance of ever being capable of learning real deep (& wide) network in a reasonable time. With that I mean network of thousands (if not hundreds of thousand or even millions) of input features and 3 or more layers , each with lesser features but still a lot. This matrix library can never efficiently handle such big matrices. See [Big Data with Elixir - #48 by bbense](https://forum.elixirforum.com/t/big-data-with-elixir/154/48) for the same discussion at length. So this can never be more than just a toy project. Sorry to burst your bubble. ---
**Author:** ![TheQuengineer](https://forum.elixirforum.com/user_avatar/forum.elixirforum.com/thequengineer/32/3448_2.png) [@TheQuengineer](https://forum.elixirforum.com/u/TheQuengineer)\ **Post date:** [February 23, 2017, 8:38pm UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818/8 "2017-02-23T20:38:51Z")
No bubble’s been burst here. I’m aware of the Matrix libraries limitations. That’s why in the post I mentioned Tensor that actually uses flow in the background instead of just using normal lists. That Matrix library was good enough for the problem set that was being illustrated in the writing. ---
**Author:** ![entone](https://forum.elixirforum.com/user_avatar/forum.elixirforum.com/entone/32/18061_2.png) [@entone](https://forum.elixirforum.com/u/entone)\ **Post date:** [February 24, 2017, 3:38am UTC](https://forum.elixirforum.com/t/deep-learning-and-artificial-intelligence-with-elixir/3818/9 "2017-02-24T03:38:30Z")
Garret Smith is building an interesting system in Erlang for running and benchmarking Tensor Flow, [http://guild.ai](http://guild.ai) He also just created a new website called [http://www.tensorflowpatterns.org/](http://www.tensorflowpatterns.org/) which has some good stuff as well, although it’s mostly Python.