https://github.com/clementetienam/ccr_piezoresponse-force-microscopy-

Using CCR to predict piezoresponse force microscopy datasets
https://github.com/clementetienam/ccr_piezoresponse-force-microscopy-

deep-neural-networks machine-learning mixture-of-experts supervised-learning

Last synced: about 2 months ago
JSON representation

Using CCR to predict piezoresponse force microscopy datasets

• Host: GitHub
• URL: https://github.com/clementetienam/ccr_piezoresponse-force-microscopy-
• Owner: clementetienam
• Created: 2019-11-11T12:34:32.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2019-11-11T12:47:45.000Z (about 5 years ago)
• Last Synced: 2024-07-30T18:01:59.793Z (6 months ago)
• Topics: deep-neural-networks, machine-learning, mixture-of-experts, supervised-learning
• Size: 35.3 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# CCR_piezoresponse-force-microscopy-

Using CCR to predict piezoresponse force microscopy datasets.

CCR which stands for Cluster, Classify, Regress is a novel method for approximating discountinous functions. In this approach, CCR is used in constructing discountinous machines for piezoresponse force microscopy data(PFM). The training.py and prediction.py script shows the individiual training and prediction steps. To retrain the machine simply run the training.py script and indicate the level of training samples needed.To predict simply run the predict.py script.

There are 2 implementation of the algorithm. Using a train case of 50% and 80% resepctively