A Gaussian Attractor Network for Memory and Recognition with Experience-Dependent Learning
A Gaussian Attractor Network for Memory and Recognition with Experience-Dependent Learning
复制标题
用于记忆和识别的高斯吸引子网络与经验依赖学习
DOI：
10.1162/neco.2010.02-09-957
复制
发表时间：
2010-05-01
影响因子：
2.9
通讯作者：
Zhang, Bo
中科院分区：
文献类型：
--
作者：
Hu, Xiaolin;Zhang, Bo
吸引子网络被广泛认为是不同物种动物记忆系统的基础。现有的模型已经成功地定性建模吸引子动力学的属性，但他们的计算能力往往遭受现实的复杂模式，虚假的吸引子，低存储容量，并难以识别吸引子的吸引力领域的穷人表示。我们提出了一个简单的两层架构，高斯吸引子网络，它没有虚假的吸引子，如果要存储的模式是不相关的，可以存储尽可能多的模式的输出层中的神经元的数量。同时，吸引场可以被精确地量化和操纵。配备经验依赖的无监督学习策略，网络可以表现出离散和连续的吸引子动态。一个基于数值模拟的可测试的预测是，大脑中存在神经元，它们最初可以区分两个相似的刺激，但在广泛暴露于物理中间刺激后就不能了。受此网络的启发，我们发现在一个著名的层次视觉识别模型HMAX中添加一些局部反馈，可以使该模型重现一些与高级视觉感知相关的最新实验结果。
Attractor networks are widely believed to underlie the memory systems of animals across different species. Existing models have succeeded in qualitatively modeling properties of attractor dynamics, but their computational abilities often suffer from poor representations for realistic complex patterns, spurious attractors, low storage capacity, and difficulty in identifying attractive fields of attractors. We propose a simple two-layer architecture, gaussian attractor network, which has no spurious attractors if patterns to be stored are uncorrelated and can store as many patterns as the number of neurons in the output layer. Meanwhile the attractive fields can be precisely quantified and manipulated. Equipped with experience-dependent unsupervised learning strategies, the network can exhibit both discrete and continuous attractor dynamics. A testable prediction based on numerical simulations is that there exist neurons in the brain that can discriminate two similar stimuli at first but cannot after extensive exposure to physically intermediate stimuli. Inspired by this network, we found that adding some local feedbacks to a well-known hierarchical visual recognition model, HMAX, can enable the model to reproduce some recent experimental results related to high-level visual perception.