The goal of this project is to build robust classifiers for the SAT-6 dataset. There are 4 notebooks in the project demonstrate the process for creating the classifiers:
eda.ipynb: The exploratory data analysis notebook. Here are the data exploration notes, visualizations, and a simple baseline model.cnn.ipynb: A deep convolutional neural network trained on SAT-6.cnn_eval.ipynb: An exploration of the neural network trained incnn.ipynb.vae.ipynb: A variational autoencoder trained on SAT-6.vae_eval: An exploration of the autoencoder and its resulting vector space created invae.ipynb.