Department of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, PR China.
Department of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, PR China.
Neural Netw. 2023 Sep;166:670-682. doi: 10.1016/j.neunet.2023.07.040. Epub 2023 Jul 31.
Associative system has attracted increasing attention for it can store basic information and then infer details to match perception with an efficient self-organization algorithm. However, the implementation of the associative system with the application of real-world data is relatively difficult. To address this issue, we propose a novel biologically inspired auto-associative (BIAA) network to explore the structure, encoding and formation of associative memory as well as to extend the ability to real-world application. Our network is constructed by imitating the organization of the cortical minicolumns where each minicolumn contains plenty of parallel biological spiking neurons. To allow the network to learn and predict one symbol per theta cycle, we incorporate synaptic delay and theta oscillation into the neuron dynamic process. Subsequently, we design a sparse temporal population (STP) coding scheme that allows each input symbol to be represented as stable, unique, and easily recallable sparsely distributed representations. By combining associative learning dynamics with the STP coding, our network realizes efficient storage and inference in an ordered manner. Experimental results indicate that the proposed network successfully performs sequence retrieval from partial text and sequence recovery from distorted information. BIAA network provides new insight into introducing biologically inspired mechanisms into associative system and has enormous potential for hardware and software applications.
联想系统因其能够存储基本信息，然后通过高效的自组织算法推断细节以匹配感知，而引起了越来越多的关注。然而，将联想系统与实际应用的数据相结合的实现相对困难。为了解决这个问题，我们提出了一种新颖的受生物启发的自联想（BIAA）网络，以探索联想记忆的结构、编码和形成，并扩展到实际应用的能力。我们的网络通过模仿皮质微柱的组织构建而成，每个微柱包含大量平行的生物尖峰神经元。为了使网络能够在每个 theta 周期学习和预测一个符号，我们将突触延迟和 theta 振荡纳入神经元动态过程中。随后，我们设计了一种稀疏时间群体（STP）编码方案，允许每个输入符号表示为稳定、独特且易于回忆的稀疏分布表示。通过将联想学习动力学与 STP 编码相结合，我们的网络以有序的方式实现了高效的存储和推断。实验结果表明，所提出的网络成功地从部分文本中进行了序列检索，并从失真信息中恢复了序列。BIAA 网络为将受生物启发的机制引入联想系统提供了新的思路，并具有巨大的硬件和软件应用潜力。
