Introduction to the theory of neural computation
Introduction to the theory of neural computation
Avoiding catastrophic forgetting by a biologically inspired dual-network memory model
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part II
| Hi-index | 0.00 |
In neural networks, when new patterns are learned by a network, the new information radically interferes with previously stored patterns. This drawback is called catastrophic forgetting or catastrophic interference. We have already proposed a biologically inspired dual-network memory model which can reduce catastrophic interference. Although two distinct networks of the model correspond to the hippocampus and the neocortex of the brain, the former was modeled by a very simple neural network. In this paper, we improve the hippocampal network of the model and examine its behavior. Computer simulation results show that the proposed hippocampal network has much better ability to store and retrieve training patterns.