# Theano tutorials?

**URL:** <https://discourse.pymc.io/t/theano-tutorials/6394>\
**Category:** Questions\
**Created:** [December 7, 2020, 6:44pm UTC](https://discourse.pymc.io/t/theano-tutorials/6394 "2020-12-07T18:44:06Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![jbuddy\_13](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/jbuddy_13/32/5900_2.png) [@jbuddy\_13](https://discourse.pymc.io/u/jbuddy_13)\
**Post date:** [December 7, 2020, 6:44pm UTC](https://discourse.pymc.io/t/theano-tutorials/6394/1 "2020-12-07T18:44:06Z")

</div>

I see that [deeplearning.net](http://deeplearning.net) has been taken down, save for a handful for pages. I’ve run into functions like the below before, which I don’t really understand what’s happening or why.

This particular function came from a PyMC3 adaptation of a 2017 Google whitepaper. For the PyMC3 code, reference link 3.

[Bayesian Methods for Media Mix Modeling with Carryover and Shape Effects – Google Research](https://research.google/pubs/pub46001/) (whitepaper)

[Bayesian Media Mix Modeling using PyMC3, for Fun and Profit | by Luca Fiaschi | HelloTech (hellofresh.com)](https://engineering.hellofresh.com/bayesian-media-mix-modeling-using-pymc3-for-fun-and-profit-2bd4667504e6) (dumbed down writeup)

[A Bayesian Approach to Media Mix Modeling by Michael Johns & Zhenyu Wang - YouTube](https://www.youtube.com/watch?v=UznM_-_760Y&t=908s) (video reviewing the writeup)

```python
def geometric_adstock(x, alpha=0.8,L=12,normalize=True):
    w = tt.as_tensor_variable([tt.power(alpha,i) for i in range(L)])
    xx = tt.stack([tt.concatenate([tt.zeros(i), x[:x.shape[0] -i]]) for i in range(L)])
   
    if not normalize:
        y = tt.dot(w,xx)
    else:
        y = tt.dot(w/tt.sum(w), xx)
    return y

```

Could someone link some fairly in-depth Theano turorials?

---

<div class="post-metadata">

**Author:** ![LegrandNico](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/legrandnico/32/5325_2.png) [@LegrandNico](https://discourse.pymc.io/u/LegrandNico)\
**Post date:** [December 7, 2020, 10:54pm UTC](https://discourse.pymc.io/t/theano-tutorials/6394/2 "2020-12-07T22:54:30Z")

</div>

Maybe this one can help:

> **[Tutorial - 《Theano 1.0 Document》 - 书栈网 · BookStack](https://www.bookstack.cn/read/Theano-1.0/a0c3ed0c825604cf.md)**

---

<div class="post-metadata">

**Author:** ![jbuddy\_13](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/jbuddy_13/32/5900_2.png) [@jbuddy\_13](https://discourse.pymc.io/u/jbuddy_13)\
**Post date:** [December 7, 2020, 11:04pm UTC](https://discourse.pymc.io/t/theano-tutorials/6394/3 "2020-12-07T23:04:07Z")

</div>

This is awesome, thank you!

---

<div class="post-metadata">

**Author:** ![junpenglao](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/junpenglao/32/8_2.png) [@junpenglao](https://discourse.pymc.io/u/junpenglao)\
**Post date:** [December 8, 2020, 6:58am UTC](https://discourse.pymc.io/t/theano-tutorials/6394/4 "2020-12-08T06:58:45Z")

</div>

See also: [https://theano-pymc.readthedocs.io/en/latest/](https://theano-pymc.readthedocs.io/en/latest/)