A biologically inspired dual-network memory model for reduction of catastrophic forgetting
A biologically inspired dual-network memory model for reduction of catastrophic forgetting
复制标题
DOI：
10.1016/j.neucom.2013.08.044
复制
发表时间：
2014-06
期刊：
影响因子：
6
通讯作者：
M. Hattori
中科院分区：
文献类型：
--
作者：
M. Hattori
当信息按顺序学习时，神经网络会遇到严重的灾难性遗忘，这对于人类记忆模型和实际工程应用来说都是不可接受的。在这项研究中，我们提出了一种新的生物启发的双网络记忆模型，可以显著减少灾难性遗忘。该模型由两个不同的神经网络组成：海马区和大脑皮层网络。信息首先存储在海马区网络中，然后传输到新皮质网络。在海马区网络中，引入了海马区CA3区神经元的混沌行为和齿状回区神经元的翻转。通过CA3的混沌回忆可以检索海马区网络中存储的信息。此后，从海马区网络检索的信息与先前存储的信息交织，并通过使用新皮质网络中的假模式进行合并。计算机仿真结果表明了所提出的双网络存储模型的有效性。
Neural networks encounter serious catastrophic forgetting when information is learned sequentially, which is unacceptable for both a model of human memory and practical engineering applications. In this study, we propose a novel biologically inspired dual-network memory model that can significantly reduce catastrophic forgetting. The proposed model consists of two distinct neural networks: hippocampal and neocortical networks. Information is first stored in the hippocampal network, and thereafter, it is transferred to the neocortical network. In the hippocampal network, chaotic behavior of neurons in the CA3 region of the hippocampus and neuronal turnover in the dentate gyrus region are introduced. Chaotic recall by CA3 enables retrieval of stored information in the hippocampal network. Thereafter, information retrieved from the hippocampal network is interleaved with previously stored information and consolidated by using pseudopatterns in the neocortical network. The computer simulation results show the effectiveness of the proposed dual-network memory model.