dingliu0305 / Tree-Tensor-Networks-in-Machine-Learning

This is the computational appendix for the following paper:

Ding Liu, Shi-Ju Ran, Peter Wittek, Cheng Peng, Raul Blázquez García, Gang Su, Maciej Lewenstein. Machine Learning by Two-Dimensional Hierarchical Tensor Networks: A Quantum Information Theoretic Perspective on Deep Architectures. arXiv:1710.04833, 2017.

The code uses tncontract for tensor contractions. Other dependencies are SciPy, Matplotlib, and Scikit-learn.

The data files can be downloaded from here.

Files

• tree_tensor_network_mnist.py: The implementation of the tree tensor network for the MNIST dataset.

• tsne_mnist.py: Plotting the t-SNE embedding.

• utilities_mnist.py: Helper functions.

• TTN_mnist.py: The main file to train and test the tree tensor network on MNIST.

• TTN_tsne.py: The script to generate the model for t-SNE embedding.