Skip to content

Apply Hyperdimensional Computing techniques to perform classification on the MNIST dataset (28x28 version and 8x8 version).

Notifications You must be signed in to change notification settings

mlpotter/Hyperdimensional_Character_Recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Recognition Performance on MNIST Binarized (large version, similar performance with small version) matching Performance Analysis of Hyperdimensional Computing for Character Recognition.

              precision    recall  f1-score   support

           0       0.91      0.85      0.88      4153
           1       0.76      0.95      0.85      4678
           2       0.86      0.75      0.80      4239
           3       0.73      0.77      0.75      4246
           4       0.75      0.82      0.79      4098
           5       0.69      0.67      0.68      3787
           6       0.87      0.83      0.85      4103
           7       0.87      0.83      0.85      4388
           8       0.80      0.71      0.75      4145
           9       0.74      0.74      0.74      4163

    accuracy                           0.80     42000
   macro avg       0.80      0.79      0.79     42000
weighted avg       0.80      0.80      0.80     42000

About

Apply Hyperdimensional Computing techniques to perform classification on the MNIST dataset (28x28 version and 8x8 version).

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages