https://github.com/haakonvt/ann-md
My master thesis: Using neural networks as hyper-potential surfaces in MD
https://github.com/haakonvt/ann-md
master-thesis neural-network tensorflow
Last synced: 9 days ago
JSON representation
My master thesis: Using neural networks as hyper-potential surfaces in MD
- Host: GitHub
- URL: https://github.com/haakonvt/ann-md
- Owner: haakonvt
- License: mit
- Created: 2016-09-21T15:47:24.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2021-01-06T15:55:27.000Z (over 4 years ago)
- Last Synced: 2025-03-29T06:42:14.988Z (about 1 month ago)
- Topics: master-thesis, neural-network, tensorflow
- Language: Python
- Homepage:
- Size: 216 KB
- Stars: 5
- Watchers: 3
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Neural Network Potential
### What is this?
This code is part of my master thesis where I look into the use of neural networks as (hyper) potential energy surface (PES) in molecular dynamics (MD). Some simple examples, like approximating a "completely" arbitrary function of 1 or 2 variables is included and was used for training my own neural network i.e. my brain to work with TensorFlow.
Some examples of how the neural network approximates a function of two variables can be seen in the videos below:
1. https://www.youtube.com/watch?v=jxhNaDR5hlE
2. https://www.youtube.com/watch?v=X3RO9oHPD-A
## Warning/FYI: This repo is severely outdated!