Add simple working example of basic TCN / MomentNetwork structure #58
Conversation
|
Thank you Jonathan, great work! We'll try and integrate your algorithm soon :) |
Codecov Report
❗ Your organization is not using the GitHub App Integration. As a result you may experience degraded service beginning May 15th. Please install the Github App Integration for your organization. Read more. Additional details and impacted files@@ Coverage Diff @@
## main #58 +/- ##
=======================================
Coverage 91.36% 91.36%
=======================================
Files 42 42
Lines 1737 1737
=======================================
Hits 1587 1587
Misses 150 150 |
…with existing classes, add example notebook, fixed typing and some linting
|
Today I worked on the code and did the following:
There is still some work to do, primarily:
|
|
@JLDC, could you give access to your fork also to @marcofavoritobi? (no hurry) |
He should already have access. Any maintainer is allowed to edit this pull request. Let me know if I am mistaken and I need to undertake something else. |
| { | ||
| "cell_type": "code", | ||
| "execution_count": 48, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "data": { | ||
| "text/plain": [ | ||
| "0.6542314" | ||
| ] | ||
| }, | ||
| "execution_count": 48, | ||
| "metadata": {}, | ||
| "output_type": "execute_result" | ||
| } | ||
| ], | ||
| "source": [ | ||
| "Y.mean()" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 50, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "data": { | ||
| "text/plain": [ | ||
| "0.19000853598117828" | ||
| ] | ||
| }, | ||
| "execution_count": 50, | ||
| "metadata": {}, | ||
| "output_type": "execute_result" | ||
| } | ||
| ], | ||
| "source": [ | ||
| "Y.std()*2 " | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [] | ||
| } |
There was a problem hiding this comment.
I guess the last cells can be removed, right? They look like "debugging cells"
| MSE_LOSS = nn.MSELoss() | ||
|
|
||
|
|
||
| # TODO: Some issues with the parameters imho, the optimizer as a Callback is not |
There was a problem hiding this comment.
an idea to solve it from ChatGPT:
https://chat.openai.com/share/43b7067f-9a6c-47a5-b2a2-9bf64b0ebd8e
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "In this tutorial we show how to use the algorithm of Chassot et al. (**TITLE**) to learn optimal moments using neural networks. " |
There was a problem hiding this comment.
can we replace TITLE with the actual paper title?
| This module contains a Moment Network implementation. | ||
|
|
||
| - Chassot, J. (2023). | ||
| Paper name |
There was a problem hiding this comment.
can we add paper title here? And the other authors?
There was a problem hiding this comment.
The title is still somewhat a working title, we might change it but if that is the case I will open a pull request. In the meanwhile, the title is "Constructing Efficient Simulated Moments Using Temporal Convolutional Networks", by Jonathan Chassot and Michael Creel. Link: https://www.jldc.ch/uploads/2023_chassot_creel.pdf
Proposed changes
Add a simple example of how a neural network (temporal convolutional network) could be used to construct the moments of a given underlying model.
Types of changes
Checklist
mainbranch (left side). Also you should start your branch off ourmain.Further comments
This is really a minimal working example somewhat outside of the package structure. It should be integrated in the package structure and the PR is being created as discussed with @AldoGl. He will make changes to this PR before integrating it.