Elastic Weight Consolidation (EWC): Nuts and Bolts
This is an incremental analysis aimed at researchers familiar with continual learning, offering deeper insights into an existing method.
The report provides theoretical support for Elastic Weight Consolidation (EWC), a method for continual learning, by disentangling the underlying concept of its objective function.
In this report, we present a theoretical support of the continual learning method \textbf{Elastic Weight Consolidation}, introduced in paper titled `Overcoming catastrophic forgetting in neural networks'. Being one of the most cited paper in regularized methods for continual learning, this report disentangles the underlying concept of the proposed objective function. We assume that the reader is aware of the basic terminologies of continual learning.