How to Prevent Catastrophic Rememberting in Connectionist Neural Networks

Catastrophic forgetting is defined as a complete forgetting of previously learned information by a neural network exposed to new information. This problem is a general problem that exists in different types of neural networks, from standard back propagation neural networks to unsupervised neural networks like self organizing as or for connectionist models of sequence acquisition. In order to prevent catastrophic forgetting, various researchers have suggested using a dual memory system,. which fundamentally simulates the presence of a short term and long term memory.