Commit d6a2b183 authored by Zhan Li's avatar Zhan Li

Merge branch 'master' of gitext.gfz-potsdam.de:ml-gfz/hackathons/20200503_gfz

parents 56e436d3 db187d74
This source diff could not be displayed because it is too large. You can view the blob instead.
For usage:
This are scripts written on the Machine Learning Hackathon on 2020-03-05
at GFZ and are mostly to get in touch with the machine learning and
deep learning techniques and tools.
You may have to change paths for loading data files, as well as install
python3 libraries (sklearn, tensorflow, keras).
If you have questions you can get write mails to:
```
dber@gfz-potsdam.de
hecken@gfz-potsdam.de
truong_tomy@yahoo.de
zali@gfz-potsdam.de
or nils.brinckmann@gfz-potsdam.de
```
Feel free to use whatever you want, but don't expect a production ready
experience.
For questions about the overall hackathon ask `jbed@gfz-potsdam.de` or
wrona@gfz-potsdam.de.
For what is in the folder:
- `Regression.ipynb` is a notebook for a linear regression
- `Neural Network.py` is an experiment to predict the SOC, clay and CaCO3
using keras and deep learning
- `Neural_Network_with_linear_model.py` is an experiment to use a linear
regression and deep learning together by predicting the residuals of
the linear regression with deep learning. Explicit: This script was
not reviewed in any kind and is very likely to be complete rubbish.
- `Neural Network.ipynb` is a notebook for a deep learning approach
- `notes.xlsx` is a table sheet to documenting the experiments and
protocol the parameters for deep learning settings.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment