Skip to content

Latest commit

 

History

History
12 lines (10 loc) · 547 Bytes

README.md

File metadata and controls

12 lines (10 loc) · 547 Bytes

EWC-python

A pure python implementation of elastic weight consolidation introduced in Overcoming catastrophic forgetting in neural networks.

Prerequisites

  • pure python implementation, no need for any machine learning framework.
  • write with python 3.6, but can run with python 2.7 after simple modification.

Running

run main.py to get start.

Result

accuracy of the network after each MNIST permutation task.