Understanding Hyperdimensional Computing for Parallel Single-Pass Learning

$ python main.py [-h] [-lr LR] [-gamma GAMMA] [-epoch EPOCH] [-gorder GORDER] [-dim DIM] 
[-data_dir DATA_DIR] [-model MODEL]
optional arguments:
  -h, --help            show this help message and exit
  -lr LR                learning rate for optimizing class representative
  -gamma GAMMA          kernel parameter for computing covariance
  -epoch EPOCH          epochs of training
  -gorder GORDER        order of the cyclic group required for G-VSA
  -dim DIM              dimension of hypervectors
  -resume               resume from existing encoded hypervectors
  -data_dir DATA_DIR    Directory used to save encoded data (hypervectors)
  -dataset {mnist,fmnist,cifar,isolet,ucihar}
                        dataset (mnist | fmnist | cifar | isolet | ucihar)
  -raw_data_dir RAW_DATA_DIR
                        Raw data directory to the dataset
  -model {rff-hdc,linear-hdc,rff-gvsa}
                        feature and model to use: (rff-hdc | linear-hdc | rff-gvsa)

$ python main.py -gamma 0.3 -epoch 10 -gorder 8 -dim 10000 -dataset mnist -model rff-gvsa