bimalb58/Logical-Tsetlin-Machine-Robustness
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
This document is a how-to for running the experiments detailed in the paper. Download MNIST-c and IMDB datasets as per instructions below. ================ Requirements ================ The main depedencies can be installed via `pip install -r requirements.txt`. ______________________________ Python 3.7.x, https://www.python.org/ Numpy, http://www.numpy.org/ PyCUDA, https://documen.tician.de/pycuda/ Scikit-learn, https://scikit-learn.org/ Keras, https://keras.io/ Tensorflow, https://www.tensorflow.org/install _______________________________________________________________ ================ Installation ================ pip install PyTsetlinMachineCUDA _______________________________________________________________ ======== Datasets ======== MNIST-C: https://zenodo.org/record/3239543#.ZBsnFnbMJNM IMDB: Can be downloaded from Keras from imdb_preprocess.py ________________________________________ ================ Preprocessing ================ The script produces .pkl file, which is later used in robustness and similarity check. $python imdb_preprocess.py $python MNIST_preprocess.py ================ Robustness ================ $python Robustness_check.py ================ Similarity ================ $python similarity_check.py ----FIN----
About
Verifying Robustness of logical tsetlin machine
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published