State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China.
Neural Comput. 2010 May;22(5):1333-57. doi: 10.1162/neco.2010.02-09-957.
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.
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对吸引子动力学的性质进行了定性建模，但它们的计算能力往往受到对现实复杂模式、虚假吸引子、低存储容量和难以识别吸引子吸引场的表示能力差的限制。我们提出了一个简单的两层架构，高斯吸引子网络，如果要存储的模式是不相关的，并且可以存储与输出层神经元数量一样多的模式，则没有虚假吸引子。同时，吸引场可以精确地量化和操纵。配备了基于经验的无监督学习策略，该网络可以表现出离散和连续的吸引子动力学。基于数值模拟的一个可测试预测是，大脑中存在一些神经元，它们最初可以区分两个相似的刺激，但在大量接触物理上中间的刺激后就无法区分了。受这个网络的启发，我们发现，向一个著名的分层视觉识别模型 HMAX 添加一些局部反馈，可以使模型再现一些与高级视觉感知相关的最近的实验结果。
