Xia Min, Wong W K, Wang Zhijie
College of Information and Control Science, Nanjing University of Information Science and Technology, Nanjing, 210044, China, and Institute of Textiles and Clothing, Hong Kong Polytechnic University, 999077, Hong Kong
Neural Comput. 2014 Dec;26(12):2944-61. doi: 10.1162/NECO_a_00663. Epub 2014 Aug 22.
Sequence information processing, for instance, the sequence memory, plays an important role on many functions of brain. In the workings of the human brain, the steady-state period is alterable. However, in the existing sequence memory models using heteroassociations, the steady-state period cannot be changed in the sequence recall. In this work, a novel neural network model for sequence memory with controllable steady-state period based on coherent spininteraction is proposed. In the proposed model, neurons fire collectively in a phase-coherent manner, which lets a neuron group respond differently to different patterns and also lets different neuron groups respond differently to one pattern. The simulation results demonstrating the performance of the sequence memory are presented. By introducing a new coherent spin-interaction sequence memory model, the steady-state period can be controlled by dimension parameters and the overlap between the input pattern and the stored patterns. The sequence storage capacity is enlarged by coherent spin interaction compared with the existing sequence memory models. Furthermore, the sequence storage capacity has an exponential relationship to the dimension of the neural network.
例如，序列信息处理，即序列记忆，在大脑的许多功能中起着重要作用。在人类大脑的运作中，稳态期是可变的。然而，在现有的使用异联想的序列记忆模型中，序列回忆时的稳态期无法改变。在这项工作中，提出了一种基于相干自旋相互作用的具有可控稳态期的新型序列记忆神经网络模型。在所提出的模型中，神经元以相位相干的方式集体放电，这使得神经元群体对不同模式有不同的反应，也使得不同的神经元群体对一种模式有不同的反应。给出了模拟结果以证明序列记忆的性能。通过引入一种新的相干自旋相互作用序列记忆模型，稳态期可以由维度参数以及输入模式与存储模式之间的重叠来控制。与现有的序列记忆模型相比，相干自旋相互作用扩大了序列存储容量。此外，序列存储容量与神经网络的维度呈指数关系。
